Neel Nanda

Publication Activity (10 Years)

Years Active: 2021-2024
Publications (10 Years): 38

Top Topics

Multiple Choice

Top Venues

Trans. Mach. Learn. Res.

Publications

Fred Zhang, Neel Nanda
Towards Best Practices of Activation Patching in Language Models: Metrics and Methods. ICLR (2024)
Stefan Heimersheim, Neel Nanda
How to use and interpret activation patching. CoRR (2024)
Bilal Chughtai, Alan Cooney, Neel Nanda
Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs. CoRR (2024)
Wes Gurnee, Theo Horsley, Zifan Carl Guo, Tara Rezaei Kheirkhah, Qinyi Sun, Will Hathaway, Neel Nanda, Dimitris Bertsimas
Universal Neurons in GPT2 Language Models. Trans. Mach. Learn. Res. 2024 (2024)
Wes Gurnee, Theo Horsley, Zifan Carl Guo, Tara Rezaei Kheirkhah, Qinyi Sun, Will Hathaway, Neel Nanda, Dimitris Bertsimas
Universal Neurons in GPT2 Language Models. CoRR (2024)
Aleksandar Makelov, Georg Lange, Atticus Geiger, Neel Nanda
Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching. ICLR (2024)
Connor Kissane, Robert Krzyzanowski, Joseph Isaac Bloom, Arthur Conmy, Neel Nanda
Interpreting Attention Layer Outputs with Sparse Autoencoders. CoRR (2024)
Jacob Dunefsky, Philippe Chlenski, Neel Nanda
Transcoders Find Interpretable LLM Feature Circuits. CoRR (2024)
Senthooran Rajamanoharan, Tom Lieberum, Nicolas Sonnerat, Arthur Conmy, Vikrant Varma, János Kramár, Neel Nanda
Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders. CoRR (2024)
Andy Arditi, Oscar Obeso, Aaquib Syed, Daniel Paleka, Nina Rimsky, Wes Gurnee, Neel Nanda
Refusal in Language Models Is Mediated by a Single Direction. CoRR (2024)
Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, Tom Lieberum, Vikrant Varma, János Kramár, Rohin Shah, Neel Nanda
Improving Dictionary Learning with Gated Sparse Autoencoders. CoRR (2024)
Aleksandar Makelov, Georg Lange, Neel Nanda
Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control. CoRR (2024)
Alessandro Stolfo, Ben Wu, Wes Gurnee, Yonatan Belinkov, Xingyi Song, Mrinmaya Sachan, Neel Nanda
Confidence Regulation Neurons in Language Models. CoRR (2024)
János Kramár, Tom Lieberum, Rohin Shah, Neel Nanda
AtP*: An efficient and scalable method for localizing LLM behaviour to components. CoRR (2024)
Cody Rushing, Neel Nanda
Explorations of Self-Repair in Language Models. CoRR (2024)
Alex Foote, Neel Nanda, Esben Kran, Ioannis Konstas, Shay Cohen, Fazl Barez
Neuron to Graph: Interpreting Language Model Neurons at Scale. CoRR (2023)
Callum McDougall, Arthur Conmy, Cody Rushing, Thomas McGrath, Neel Nanda
Copy Suppression: Comprehensively Understanding an Attention Head. CoRR (2023)
Lucia Quirke, Lovis Heindrich, Wes Gurnee, Neel Nanda
Training Dynamics of Contextual N-Grams in Language Models. CoRR (2023)
Tom Lieberum, Matthew Rahtz, János Kramár, Neel Nanda, Geoffrey Irving, Rohin Shah, Vladimir Mikulik
Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla. CoRR (2023)
Neel Nanda, Andrew Lee, Martin Wattenberg
Emergent Linear Representations in World Models of Self-Supervised Sequence Models. CoRR (2023)
Wes Gurnee, Neel Nanda, Matthew Pauly, Katherine Harvey, Dmitrii Troitskii, Dimitris Bertsimas
Finding Neurons in a Haystack: Case Studies with Sparse Probing. CoRR (2023)
Bilal Chughtai, Lawrence Chan, Neel Nanda
A Toy Model of Universality: Reverse Engineering how Networks Learn Group Operations. ICML (2023)
Neel Nanda, Lawrence Chan, Tom Lieberum, Jess Smith, Jacob Steinhardt
Progress measures for grokking via mechanistic interpretability. ICLR (2023)
Neel Nanda, Lawrence Chan, Tom Lieberum, Jess Smith, Jacob Steinhardt
Progress measures for grokking via mechanistic interpretability. CoRR (2023)
Curt Tigges, Oskar John Hollinsworth, Atticus Geiger, Neel Nanda
Linear Representations of Sentiment in Large Language Models. CoRR (2023)
Wes Gurnee, Neel Nanda, Matthew Pauly, Katherine Harvey, Dmitrii Troitskii, Dimitris Bertsimas
Finding Neurons in a Haystack: Case Studies with Sparse Probing. Trans. Mach. Learn. Res. 2023 (2023)
Neel Nanda, Andrew Lee, Martin Wattenberg
Emergent Linear Representations in World Models of Self-Supervised Sequence Models. BlackboxNLP@EMNLP (2023)
Aleksandar Makelov, Georg Lange, Neel Nanda
Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching. CoRR (2023)
Bilal Chughtai, Lawrence Chan, Neel Nanda
A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations. CoRR (2023)
Fred Zhang, Neel Nanda
Towards Best Practices of Activation Patching in Language Models: Metrics and Methods. CoRR (2023)
Alex Foote, Neel Nanda, Esben Kran, Ionnis Konstas, Fazl Barez
N2G: A Scalable Approach for Quantifying Interpretable Neuron Representations in Large Language Models. CoRR (2023)
Michael K. Cohen, Marcus Hutter, Neel Nanda
Fully General Online Imitation Learning. J. Mach. Learn. Res. 23 (2022)
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
In-context Learning and Induction Heads. CoRR (2022)
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
Predictability and Surprise in Large Generative Models. CoRR (2022)
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
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback. CoRR (2022)
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 Brown, Jared Kaplan, Sam McCandlish, Christopher Olah, Dario Amodei, Jack Clark
Predictability and Surprise in Large Generative Models. FAccT (2022)
Neel Nanda, Jonathan Uesato, Sven Gowal
An Empirical Investigation of Learning from Biased Toxicity Labels. CoRR (2021)
Michael K. Cohen, Marcus Hutter, Neel Nanda
Fully General Online Imitation Learning. CoRR (2021)