Thomas McGrath

According to our database, Thomas McGrath authored at least 20 papers between 2019 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space.

Eric J. Bigelow, Raphaël Sarfati, Daniel Wurgaft, Owen Lewis, Thomas McGrath, Jack Merullo, Atticus Geiger, Ekdeep Singh Lubana

CoRR, May, 2026

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior.

Daniel Wurgaft, Can Rager, Matthew Kowal, Vasudev Shyam, Sheridan Feucht, Usha Bhalla, Tal Haklay, Eric J. Bigelow, Raphaël Sarfati, Thomas McGrath, Owen Lewis, Jack Merullo, Noah D. Goodman, Thomas Fel, Atticus Geiger, Ekdeep Singh Lubana

CoRR, May, 2026

Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts.

Sheridan Feucht, Tal Haklay, Usha Bhalla, Daniel Wurgaft, Can Rager, Raphaël Sarfati, Jack Merullo, Thomas McGrath, Owen Lewis, Ekdeep Singh Lubana, Thomas Fel, Atticus Geiger

CoRR, May, 2026

Shifting the Gradient: Understanding How Defensive Training Methods Protect Language Model Integrity.

Satchel Grant, Victor Gillioz, Jake Ward, Thomas McGrath

CoRR, April, 2026

Features as Rewards: Scalable Supervision for Open-Ended Tasks via Interpretability.

Aaditya Vikram Prasad, Connor Watts, Jack Merullo, Dhruvil Gala, Owen Lewis, Thomas McGrath, Ekdeep Singh Lubana

CoRR, February, 2026

The Shape of Beliefs: Geometry, Dynamics, and Interventions along Representation Manifolds of Language Models' Posteriors.

Raphaël Sarfati, Eric J. Bigelow, Daniel Wurgaft, Jack Merullo, Atticus Geiger, Owen Lewis, Tom McGrath, Ekdeep Singh Lubana

CoRR, February, 2026

2025

Understanding sparse autoencoder scaling in the presence of feature manifolds.

Eric J. Michaud, Liv Gorton, Tom McGrath

CoRR, September, 2025

Competitive secretary problem.

Tom McGrath, Marc Schröder

Int. J. Game Theory, June, 2025

Open Problems in Mechanistic Interpretability.

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

Trans. Mach. Learn. Res., 2025

2023

Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero.

Lisa Schut, Nenad Tomasev, Tom McGrath, Demis Hassabis, Ulrich Paquet, Been Kim

CoRR, 2023

Copy Suppression: Comprehensively Understanding an Attention Head.

Callum McDougall, Arthur Conmy, Cody Rushing, Thomas McGrath, Neel Nanda

CoRR, 2023

The Hydra Effect: Emergent Self-repair in Language Model Computations.

Thomas McGrath, Matthew Rahtz, János Kramár, Vladimir Mikulik, Shane Legg

CoRR, 2023

Tracr: Compiled Transformers as a Laboratory for Interpretability.

David Lindner, János Kramár, Matthew Rahtz, Thomas McGrath, Vladimir Mikulik

CoRR, 2023

Tracr: Compiled Transformers as a Laboratory for Interpretability.

David Lindner, János Kramár, Sebastian Farquhar, Matthew Rahtz, Tom McGrath, Vladimir Mikulik

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2021

Resonant-Tunnelling Diodes as PUF Building Blocks.

Ibrahim Ethem Bagci, Thomas McGrath, Christine Barthelmes, Scott Dean, RamÓn Bernardo Gavito, Robert J. Young, Utz Roedig

IEEE Trans. Emerg. Top. Comput., 2021

Acquisition of Chess Knowledge in AlphaZero.

Thomas McGrath, Andrei Kapishnikov, Nenad Tomasev, Adam Pearce, Demis Hassabis, Been Kim, Ulrich Paquet, Vladimir Kramnik

CoRR, 2021

Causal Analysis of Agent Behavior for AI Safety.

Grégoire Delétang, Jordi Grau-Moya, Miljan Martic, Tim Genewein, Tom McGrath, Vladimir Mikulik, Markus Kunesch, Shane Legg, Pedro A. Ortega

CoRR, 2021

2020

Algorithms for Causal Reasoning in Probability Trees.

Tim Genewein, Tom McGrath, Grégoire Delétang, Vladimir Mikulik, Miljan Martic, Shane Legg, Pedro A. Ortega

CoRR, 2020

Meta-trained agents implement Bayes-optimal agents.

Vladimir Mikulik, Grégoire Delétang, Tom McGrath, Tim Genewein, Miljan Martic, Shane Legg, Pedro A. Ortega

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

Meta-learning of Sequential Strategies.

Pedro A. Ortega, Jane X. Wang, Mark Rowland, Tim Genewein, Zeb Kurth-Nelson, Razvan Pascanu, Nicolas Heess, Joel Veness, Alexander Pritzel, Pablo Sprechmann, Siddhant M. Jayakumar, Tom McGrath, Kevin J. Miller, Mohammad Gheshlaghi Azar, Ian Osband, Neil C. Rabinowitz, András György, Silvia Chiappa, Simon Osindero, Yee Whye Teh, Hado van Hasselt, Nando de Freitas, Matthew M. Botvinick, Shane Legg

CoRR, 2019