| Acquisition of chess knowledge in alphazero T McGrath, A Kapishnikov, N Tomašev, A Pearce, M Wattenberg, ... Proceedings of the National Academy of Sciences 119 (47), e2206625119, 2022 | 153 | 2022 |
| Meta-learning of sequential strategies PA Ortega, JX Wang, M Rowland, T Genewein, Z Kurth-Nelson, ... arXiv preprint arXiv:1905.03030, 2019 | 92 | 2019 |
| Biochemical machines for the interconversion of mutual information and work T McGrath, NS Jones, PR Ten Wolde, TE Ouldridge Physical review letters 118 (2), 028101, 2017 | 68 | 2017 |
| Tracr: Compiled transformers as a laboratory for interpretability D Lindner, J Kramár, S Farquhar, M Rahtz, T McGrath, V Mikulik Advances in Neural Information Processing Systems 36, 2024 | 44 | 2024 |
| Meta-trained agents implement bayes-optimal agents V Mikulik, G Delétang, T McGrath, T Genewein, M Martic, S Legg, ... Advances in neural information processing systems 33, 18691-18703, 2020 | 40 | 2020 |
| The hydra effect: Emergent self-repair in language model computations T McGrath, M Rahtz, J Kramar, V Mikulik, S Legg arXiv preprint arXiv:2307.15771, 2023 | 34 | 2023 |
| Copy suppression: Comprehensively understanding an attention head C McDougall, A Conmy, C Rushing, T McGrath, N Nanda arXiv preprint arXiv:2310.04625, 2023 | 21 | 2023 |
| Algorithms for causal reasoning in probability trees T Genewein, T McGrath, G Delétang, V Mikulik, M Martic, S Legg, ... arXiv preprint arXiv:2010.12237, 2020 | 20 | 2020 |
| Bridging the human-ai knowledge gap: Concept discovery and transfer in alphazero L Schut, N Tomasev, T McGrath, D Hassabis, U Paquet, B Kim arXiv preprint arXiv:2310.16410, 2023 | 16 | 2023 |
| Predicting human deliberative judgments with machine learning O Evans, A Stuhlmüller, C Cundy, R Carey, Z Kenton, T McGrath, ... Future of Humanity Institute, 2018 | 15 | 2018 |
| Causal analysis of agent behavior for ai safety G Déletang, J Grau-Moya, M Martic, T Genewein, T McGrath, V Mikulik, ... arXiv preprint arXiv:2103.03938, 2021 | 10 | 2021 |
| Quantitative approaches to energy and glucose homeostasis: machine learning and modelling for precision understanding and prediction T McGrath, KG Murphy, NS Jones Journal of The Royal Society Interface 15 (138), 20170736, 2018 | 10 | 2018 |
| The homeostatic dynamics of feeding behaviour identify novel mechanisms of anorectic agents TM McGrath, E Spreckley, AF Rodriguez, C Viscomi, A Alamshah, ... PLoS Biology 17 (12), e3000482, 2019 | 4 | 2019 |
| Entropy generation during computation-is it really avoidable, even in principle? T Ouldridge, R Brittain, N Jones, T McGrath APS March Meeting Abstracts 2022, Y09. 001, 2022 | | 2022 |
| Energetics, information, and self-regulation TM McGrath Imperial College London, 2020 | | 2020 |
| Interpreting, forecasting, and controlling feeding behaviour using high-resolution data TM McGrath, E Spreckley, AF Rodriguez, C Viscomi, A Alamshah, ... bioRxiv, 578344, 2019 | | 2019 |
| The homeostatic dynamics of feeding behaviour identify novel mechanisms of anorectic agents-Supplementary Material TM McGrath, E Spreckley, AF Rodriguez, C Viscomi, A Alamshah, ... | | |
| Meta-learning of Sequential Strategies Meta-learning of Sequential Strategies PA Ortega, JX Wang, M Rowland, T Genewein, Z Kurth-Nelson, ... | | |
