Neel Nanda - RankMe

93 papers A* 17Journal 74Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Building Production-Ready Probes For Gemini. CoRR János Kramár, Joshua Engels, Zheng Wang, Bilal Chughtai, Rohin Shah, Neel Nanda, Arthur Conmy
2026	J	`jnl`	Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation. CoRR Helena Casademunt, Bartosz Cywinski, Khoi Tran, Arya Jakkli, Samuel Marks, Neel Nanda
2026	J	`jnl`	Emergent Misalignment is Easy, Narrow Misalignment is Hard. CoRR Anna Soligo, Edward Turner, Senthooran Rajamanoharan, Neel Nanda
2026	J	`jnl`	Simple LLM Baselines are Competitive for Model Diffing. CoRR Elias Kempf, Simon Schrodi, Bartosz Cywinski, Thomas Brox, Neel Nanda, Arthur Conmy
2026	J	`jnl`	What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering. CoRR Jim Maar, Denis Paperno, Callum McDougall, Neel Nanda
2025	J	`jnl`	An Approach to Technical AGI Safety and Security. CoRR Rohin Shah, Alex Irpan, Alexander Matt Turner, Anna Wang, Arthur Conmy, David Lindner, Jonah Brown-Cohen, Lewis Ho, Neel Nanda, Raluca Ada Popa, Rishub Jain, Rory Greig, Samuel Albanie, Scott Emmons, Sebastian Farquhar, Sébastien Krier, Senthooran Rajamanoharan, Sophie Bridgers, Tobi Ijitoye, Tom Everitt, Victoria Krakovna, Vikrant Varma, Vladimir Mikulik, Zachary Kenton, Dave Orr, Shane Legg, Noah D. Goodman, Allan Dafoe, Four Flynn, Anca D. Dragan
2025	A*	`conf`	Are Sparse Autoencoders Useful? A Case Study in Sparse Probing. ICML Subhash Kantamneni, Joshua Engels, Senthooran Rajamanoharan, Max Tegmark, Neel Nanda
2025	J	`jnl`	Are Sparse Autoencoders Useful? A Case Study in Sparse Probing. CoRR Subhash Kantamneni, Joshua Engels, Senthooran Rajamanoharan, Max Tegmark, Neel Nanda
2025	J	`jnl`	Base Models Know How to Reason, Thinking Models Learn When. CoRR Constantin Venhoff, Iván Arcuschin, Philip Torr, Arthur Conmy, Neel Nanda
2025	J	`jnl`	Because we have LLMs, we Can and Should Pursue Agentic Interpretability. CoRR Been Kim, John Hewitt, Neel Nanda, Noah Fiedel, Oyvind Tafjord
2025	J	`jnl`	Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety. CoRR Tomek Korbak, Mikita Balesni, Elizabeth Barnes, Yoshua Bengio, Joe Benton, Joseph Bloom, Mark Chen, Alan Cooney, Allan Dafoe, Anca D. Dragan, Scott Emmons, Owain Evans, David Farhi, Ryan Greenblatt, Dan Hendrycks, Marius Hobbhahn, Evan Hubinger, Geoffrey Irving, Erik Jenner, Daniel Kokotajlo, Victoria Krakovna, Shane Legg, David Lindner, David Luan, Aleksander Madry, Julian Michael, Neel Nanda, Dave Orr, Jakub Pachocki, Ethan Perez, Mary Phuong, Fabien Roger, Joshua Saxe, Buck Shlegeris, Martín Soto, Eric Steinberger, Jasmine Wang, Wojciech Zaremba, Bowen Baker, Rohin Shah, Vladimir Mikulik
2025	J	`jnl`	Chain-of-Thought Reasoning In The Wild Is Not Always Faithful. CoRR Iván Arcuschin, Jett Janiak, Robert Krzyzanowski, Senthooran Rajamanoharan, Neel Nanda, Arthur Conmy
2025	J	`jnl`	Convergent Linear Representations of Emergent Misalignment. CoRR Anna Soligo, Edward Turner, Senthooran Rajamanoharan, Neel Nanda
2025	J	`jnl`	Difficulties with Evaluating a Deception Detector for AIs. CoRR Lewis Smith, Bilal Chughtai, Neel Nanda
2025	A*	`conf`	Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models. ICLR Javier Ferrando, Oscar Balcells Obeso, Senthooran Rajamanoharan, Neel Nanda
2025	J	`jnl`	Eliciting Secret Knowledge from Language Models. CoRR Bartosz Cywinski, Emil Ryd, Rowan Wang, Senthooran Rajamanoharan, Neel Nanda, Arthur Conmy, Samuel Marks
2025	J	`jnl`	How Visual Representations Map to Language Feature Space in Multimodal LLMs. CoRR Constantin Venhoff, Ashkan Khakzar, Sonia Joseph, Philip Torr, Neel Nanda
2025	A*	`conf`	Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models. ICML Patrick Leask, Neel Nanda, Noura Al Moubayed
2025	J	`jnl`	Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models. CoRR Patrick Leask, Neel Nanda, Noura Al Moubayed
2025	J	`jnl`	Internal states before wait modulate reasoning patterns. CoRR Dmitrii Troitskii, Koyena Pal, Chris Wendler, Callum McDougall, Neel Nanda
2025	J	`jnl`	Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit. CoRR Nick Jiang, Xiaoqing Sun, Lisa Dunlap, Lewis Smith, Neel Nanda
2025	A*	`conf`	Learning Multi-Level Features with Matryoshka Sparse Autoencoders. ICML Bart Bussmann, Noa Nabeshima, Adam Karvonen, Neel Nanda
2025	J	`jnl`	Learning Multi-Level Features with Matryoshka Sparse Autoencoders. CoRR Bart Bussmann, Noa Nabeshima, Adam Karvonen, Neel Nanda
2025	J	`jnl`	Model Organisms for Emergent Misalignment. CoRR Edward Turner, Anna Soligo, Mia Taylor, Senthooran Rajamanoharan, Neel Nanda
2025	J	`jnl`	Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences. CoRR Julian Minder, Clément Dumas, Stewart Slocum, Helena Casademunt, Cameron Holmes, Robert West, Neel Nanda
2025	J	`jnl`	Open Problems in Mechanistic Interpretability. CoRR Lee Sharkey, Bilal Chughtai, Joshua Batson, Jack Lindsey, Jeff Wu, Lucius Bushnaq, Nicholas Goldowsky-Dill, Stefan Heimersheim, Alejandro Ortega, Joseph Isaac Bloom, Stella Biderman, Adrià Garriga-Alonso, Arthur Conmy, Neel Nanda, Jessica Rumbelow, Martin Wattenberg, Nandi Schoots, Joseph Miller, Eric J. Michaud, Stephen Casper, Max Tegmark, William Saunders, David Bau, Eric Todd, Atticus Geiger, Mor Geva, Jesse Hoogland, Daniel Murfet, Tom McGrath
2025	J	`jnl`	Open Problems in Mechanistic Interpretability. Trans. Mach. Learn. Res. Lee Sharkey, Bilal Chughtai, Joshua Batson, Jack Lindsey, Jeffrey Wu, Lucius Bushnaq, Nicholas Goldowsky-Dill, Stefan Heimersheim, Alejandro Ortega, Joseph Isaac Bloom, Stella Biderman, Adrià Garriga-Alonso, Arthur Conmy, Neel Nanda, Jessica Rumbelow, Martin Wattenberg, Nandi Schoots, Joseph Miller, William Saunders, Eric J. Michaud, Stephen Casper, Max Tegmark, David Bau, Eric Todd, Atticus Geiger, Mor Geva, Jesse Hoogland, Daniel Murfet, Tom McGrath
2025	J	`jnl`	Real-Time Detection of Hallucinated Entities in Long-Form Generation. CoRR Oscar Obeso, Andy Arditi, Javier Ferrando, Joshua Freeman, Cameron Holmes, Neel Nanda
2025	J	`jnl`	Reasoning-Finetuning Repurposes Latent Representations in Base Models. CoRR Jake Ward, Chuqiao Lin, Constantin Venhoff, Neel Nanda
2025	J	`jnl`	RelP: Faithful and Efficient Circuit Discovery via Relevance Patching. CoRR Farnoush Rezaei Jafari, Oliver Eberle, Ashkan Khakzar, Neel Nanda
2025	J	`jnl`	Robustly identifying concepts introduced during chat fine-tuning using crosscoders. CoRR Julian Minder, Clément Dumas, Caden Juang, Bilal Chugtai, Neel Nanda
2025	A*	`conf`	SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability. ICML Adam Karvonen, Can Rager, Johnny Lin, Curt Tigges, Joseph Isaac Bloom, David Chanin, Yeu-Tong Lau, Eoin Farrell, Callum McDougall, Kola Ayonrinde, Demian Till, Matthew Wearden, Arthur Conmy, Samuel Marks, Neel Nanda
2025	J	`jnl`	SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability. CoRR Adam Karvonen, Can Rager, Johnny Lin, Curt Tigges, Joseph Isaac Bloom, David Chanin, Yeu-Tong Lau, Eoin Farrell, Callum McDougall, Kola Ayonrinde, Matthew Wearden, Arthur Conmy, Samuel Marks, Neel Nanda
2025	A*	`conf`	Scaling Sparse Feature Circuits For Studying In-Context Learning. ICML Dmitrii Kharlapenko, Stepan Shabalin, Arthur Conmy, Neel Nanda
2025	J	`jnl`	Scaling sparse feature circuit finding for in-context learning. CoRR Dmitrii Kharlapenko, Stepan Shabalin, Fazl Barez, Arthur Conmy, Neel Nanda
2025	J	`jnl`	Simple Mechanistic Explanations for Out-Of-Context Reasoning. CoRR Atticus Wang, Joshua Engels, Oliver Clive-Griffin, Senthooran Rajamanoharan, Neel Nanda
2025	A*	`conf`	Sparse Autoencoders Do Not Find Canonical Units of Analysis. ICLR Patrick Leask, Bart Bussmann, Michael T. Pearce, Joseph Isaac Bloom, Curt Tigges, Noura Al Moubayed, Lee Sharkey, Neel Nanda
2025	J	`jnl`	Sparse Autoencoders Do Not Find Canonical Units of Analysis. CoRR Patrick Leask, Bart Bussmann, Michael T. Pearce, Joseph Isaac Bloom, Curt Tigges, Noura Al Moubayed, Lee Sharkey, Neel Nanda
2025	J	`jnl`	Steering Evaluation-Aware Language Models to Act Like They Are Deployed. CoRR Tim Tian Hua, Andrew Qin, Samuel Marks, Neel Nanda
2025	J	`jnl`	Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning. CoRR Helena Casademunt, Caden Juang, Adam Karvonen, Samuel Marks, Senthooran Rajamanoharan, Neel Nanda
2025	J	`jnl`	Thought Anchors: Which LLM Reasoning Steps Matter? CoRR Paul C. Bogdan, Uzay Macar, Neel Nanda, Arthur Conmy
2025	J	`jnl`	Thought Branches: Interpreting LLM Reasoning Requires Resampling. CoRR Uzay Macar, Paul C. Bogdan, Senthooran Rajamanoharan, Neel Nanda
2025	J	`jnl`	Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval. CoRR Constantin Venhoff, Ashkan Khakzar, Sonia Joseph, Philip Torr, Neel Nanda
2025	A*	`conf`	Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control. ICLR Aleksandar Makelov, Georg Lange, Neel Nanda
2025	J	`jnl`	Towards eliciting latent knowledge from LLMs with mechanistic interpretability. CoRR Bartosz Cywinski, Emil Ryd, Senthooran Rajamanoharan, Neel Nanda
2025	J	`jnl`	Understanding Reasoning in Thinking Language Models via Steering Vectors. CoRR Constantin Venhoff, Iván Arcuschin, Philip Torr, Arthur Conmy, Neel Nanda
2024	J	`jnl`	AtP*: An efficient and scalable method for localizing LLM behaviour to components. CoRR János Kramár, Tom Lieberum, Rohin Shah, Neel Nanda
2024	J	`jnl`	BatchTopK Sparse Autoencoders. CoRR Bart Bussmann, Patrick Leask, Neel Nanda
2024	A*	`conf`	Confidence Regulation Neurons in Language Models. NeurIPS Alessandro Stolfo, Ben Wu, Wes Gurnee, Yonatan Belinkov, Xingyi Song, Mrinmaya Sachan, Neel Nanda
2024	J	`jnl`	Confidence Regulation Neurons in Language Models. CoRR Alessandro Stolfo, Ben Wu, Wes Gurnee, Yonatan Belinkov, Xingyi Song, Mrinmaya Sachan, Neel Nanda
2024	J	`jnl`	Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models. CoRR Javier Ferrando, Oscar Obeso, Senthooran Rajamanoharan, Neel Nanda
2024	J	`jnl`	Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks. CoRR Adam Karvonen, Can Rager, Samuel Marks, Neel Nanda
2024	A*	`conf`	Explorations of Self-Repair in Language Models. ICML Cody Rushing, Neel Nanda
2024	J	`jnl`	Explorations of Self-Repair in Language Models. CoRR Cody Rushing, Neel Nanda
2024	J	`jnl`	Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2. CoRR Tom Lieberum, Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, Nicolas Sonnerat, Vikrant Varma, János Kramár, Anca D. Dragan, Rohin Shah, Neel Nanda
2024	J	`jnl`	How to use and interpret activation patching. CoRR Stefan Heimersheim, Neel Nanda
2024	J	`jnl`	Improving Dictionary Learning with Gated Sparse Autoencoders. CoRR Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, Tom Lieberum, Vikrant Varma, János Kramár, Rohin Shah, Neel Nanda
2024	A*	`conf`	Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders. NeurIPS Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, Tom Lieberum, Vikrant Varma, János Kramár, Rohin Shah, Neel Nanda
2024	J	`jnl`	Interpreting Attention Layer Outputs with Sparse Autoencoders. CoRR Connor Kissane, Robert Krzyzanowski, Joseph Isaac Bloom, Arthur Conmy, Neel Nanda
2024	A*	`conf`	Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching. ICLR Aleksandar Makelov, Georg Lange, Atticus Geiger, Neel Nanda
2024	J	`jnl`	Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders. CoRR Senthooran Rajamanoharan, Tom Lieberum, Nicolas Sonnerat, Arthur Conmy, Vikrant Varma, János Kramár, Neel Nanda
2024	A*	`conf`	Refusal in Language Models Is Mediated by a Single Direction. NeurIPS Andy Arditi, Oscar Obeso, Aaquib Syed, Daniel Paleka, Nina Panickssery, Wes Gurnee, Neel Nanda
2024	J	`jnl`	Refusal in Language Models Is Mediated by a Single Direction. CoRR Andy Arditi, Oscar Obeso, Aaquib Syed, Daniel Paleka, Nina Rimsky, Wes Gurnee, Neel Nanda
2024	J	`jnl`	Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs. CoRR Bilal Chughtai, Alan Cooney, Neel Nanda
2024	A*	`conf`	Towards Best Practices of Activation Patching in Language Models: Metrics and Methods. ICLR Fred Zhang, Neel Nanda
2024	J	`jnl`	Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control. CoRR Aleksandar Makelov, Georg Lange, Neel Nanda
2024	J	`jnl`	Transcoders Find Interpretable LLM Feature Circuits. CoRR Jacob Dunefsky, Philippe Chlenski, Neel Nanda
2024	A*	`conf`	Transcoders find interpretable LLM feature circuits. NeurIPS Jacob Dunefsky, Philippe Chlenski, Neel Nanda
2024	J	`jnl`	Universal Neurons in GPT2 Language Models. CoRR Wes Gurnee, Theo Horsley, Zifan Carl Guo, Tara Rezaei Kheirkhah, Qinyi Sun, Will Hathaway, Neel Nanda, Dimitris Bertsimas
2024	J	`jnl`	Universal Neurons in GPT2 Language Models. Trans. Mach. Learn. Res. Wes Gurnee, Theo Horsley, Zifan Carl Guo, Tara Rezaei Kheirkhah, Qinyi Sun, Will Hathaway, Neel Nanda, Dimitris Bertsimas
2023	J	`jnl`	A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations. CoRR Bilal Chughtai, Lawrence Chan, Neel Nanda
2023	A*	`conf`	A Toy Model of Universality: Reverse Engineering how Networks Learn Group Operations. ICML Bilal Chughtai, Lawrence Chan, Neel Nanda
2023	J	`jnl`	Copy Suppression: Comprehensively Understanding an Attention Head. CoRR Callum McDougall, Arthur Conmy, Cody Rushing, Thomas McGrath, Neel Nanda
2023	J	`jnl`	Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla. CoRR Tom Lieberum, Matthew Rahtz, János Kramár, Neel Nanda, Geoffrey Irving, Rohin Shah, Vladimir Mikulik
2023	—	`conf`	Emergent Linear Representations in World Models of Self-Supervised Sequence Models. BlackboxNLP@EMNLP Neel Nanda, Andrew Lee, Martin Wattenberg
2023	J	`jnl`	Emergent Linear Representations in World Models of Self-Supervised Sequence Models. CoRR Neel Nanda, Andrew Lee, Martin Wattenberg
2023	J	`jnl`	Finding Neurons in a Haystack: Case Studies with Sparse Probing. CoRR Wes Gurnee, Neel Nanda, Matthew Pauly, Katherine Harvey, Dmitrii Troitskii, Dimitris Bertsimas
2023	J	`jnl`	Finding Neurons in a Haystack: Case Studies with Sparse Probing. Trans. Mach. Learn. Res. Wes Gurnee, Neel Nanda, Matthew Pauly, Katherine Harvey, Dmitrii Troitskii, Dimitris Bertsimas
2023	J	`jnl`	Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching. CoRR Aleksandar Makelov, Georg Lange, Neel Nanda
2023	J	`jnl`	Linear Representations of Sentiment in Large Language Models. CoRR Curt Tigges, Oskar John Hollinsworth, Atticus Geiger, Neel Nanda
2023	J	`jnl`	N2G: A Scalable Approach for Quantifying Interpretable Neuron Representations in Large Language Models. CoRR Alex Foote, Neel Nanda, Esben Kran, Ioannis Konstas, Fazl Barez
2023	J	`jnl`	Neuron to Graph: Interpreting Language Model Neurons at Scale. CoRR Alex Foote, Neel Nanda, Esben Kran, Ioannis Konstas, Shay B. Cohen, Fazl Barez
2023	A*	`conf`	Progress measures for grokking via mechanistic interpretability. ICLR Neel Nanda, Lawrence Chan, Tom Lieberum, Jess Smith, Jacob Steinhardt
2023	J	`jnl`	Progress measures for grokking via mechanistic interpretability. CoRR Neel Nanda, Lawrence Chan, Tom Lieberum, Jess Smith, Jacob Steinhardt
2023	J	`jnl`	Towards Best Practices of Activation Patching in Language Models: Metrics and Methods. CoRR Fred Zhang, Neel Nanda
2023	J	`jnl`	Training Dynamics of Contextual N-Grams in Language Models. CoRR Lucia Quirke, Lovis Heindrich, Wes Gurnee, Neel Nanda
2022	J	`jnl`	Fully General Online Imitation Learning. J. Mach. Learn. Res. Michael K. Cohen, Marcus Hutter, Neel Nanda
2022	J	`jnl`	In-context Learning and Induction Heads. CoRR Catherine Olsson, Nelson Elhage, Neel Nanda, Nicholas Joseph, Nova DasSarma, Tom Henighan, Ben Mann, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, Dawn Drain, Deep Ganguli, Zac Hatfield-Dodds, Danny Hernandez, Scott Johnston, Andy Jones, Jackson Kernion, Liane Lovitt, Kamal Ndousse, Dario Amodei, Tom Brown, Jack Clark, Jared Kaplan, Sam McCandlish, Chris Olah
2022	—	`conf`	Predictability and Surprise in Large Generative Models. FAccT Deep Ganguli, Danny Hernandez, Liane Lovitt, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, Nova DasSarma, Dawn Drain, Nelson Elhage, Sheer El Showk, Stanislav Fort, Zac Hatfield-Dodds, Tom Henighan, Scott Johnston, Andy Jones, Nicholas Joseph, Jackson Kernian, Shauna Kravec, Ben Mann, Neel Nanda, Kamal Ndousse, Catherine Olsson, Daniela Amodei, Tom B. Brown, Jared Kaplan, Sam McCandlish, Christopher Olah, Dario Amodei, Jack Clark
2022	J	`jnl`	Predictability and Surprise in Large Generative Models. CoRR Deep Ganguli, Danny Hernandez, Liane Lovitt, Nova DasSarma, Tom Henighan, Andy Jones, Nicholas Joseph, Jackson Kernion, Benjamin Mann, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, Dawn Drain, Nelson Elhage, Sheer El Showk, Stanislav Fort, Zac Hatfield-Dodds, Scott Johnston, Shauna Kravec, Neel Nanda, Kamal Ndousse, Catherine Olsson, Daniela Amodei, Dario Amodei, Tom B. Brown, Jared Kaplan, Sam McCandlish, Chris Olah, Jack Clark
2022	J	`jnl`	Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback. CoRR Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, Nicholas Joseph, Saurav Kadavath, Jackson Kernion, Tom Conerly, Sheer El Showk, Nelson Elhage, Zac Hatfield-Dodds, Danny Hernandez, Tristan Hume, Scott Johnston, Shauna Kravec, Liane Lovitt, Neel Nanda, Catherine Olsson, Dario Amodei, Tom B. Brown, Jack Clark, Sam McCandlish, Chris Olah, Benjamin Mann, Jared Kaplan
2021	J	`jnl`	An Empirical Investigation of Learning from Biased Toxicity Labels. CoRR Neel Nanda, Jonathan Uesato, Sven Gowal
2021	J	`jnl`	Fully General Online Imitation Learning. CoRR Michael K. Cohen, Marcus Hutter, Neel Nanda