| Scaling monosemanticity: Extracting interpretable features from Claude 3 Sonnet A Templeton, T Conerly, J Marcus, J Lindsey, T Bricken, B Chen, ... Anthropic, 2024 | 639 | 2024 |
| Cognitive architectures for language agents TR Sumers*, S Yao*, K Narasimhan, TL Griffiths Transactions on Machine Learning Research, 2023 | 502 | 2023 |
| Shared functional specialization in transformer-based language models and the human brain S Kumar*, TR Sumers*, T Yamakoshi, A Goldstein, U Hasson, KA Norman, ... Nature communications 15 (1), 5523, 2024 | 123* | 2024 |
| Constitutional classifiers: Defending against universal jailbreaks across thousands of hours of red teaming M Sharma, M Tong, J Mu, J Wei, J Kruthoff, S Goodfriend, E Ong, A Peng, ... arXiv preprint arXiv:2501.18837, 2025 | 89 | 2025 |
| Learning rewards from linguistic feedback TR Sumers, MK Ho, RD Hawkins, K Narasimhan, TL Griffiths Proceedings of the AAAI Conference on Artificial Intelligence 35 (7), 6002-6010, 2021 | 70 | 2021 |
| Complex cognitive algorithms preserved by selective social learning in experimental populations B Thompson, B Van Opheusden, T Sumers, TL Griffiths Science 376 (6588), 95-98, 2022 | 66 | 2022 |
| Reconciling truthfulness and relevance as epistemic and decision-theoretic utility. TR Sumers, MK Ho, TL Griffiths, RD Hawkins Psychological Review, 2023 | 59* | 2023 |
| Words are all you need? Language as an approximation for human similarity judgments R Marjieh, P Van Rijn, I Sucholutsky, T Sumers, H Lee, TL Griffiths, ... The Eleventh International Conference on Learning Representations, 2023 | 57* | 2023 |
| Clio: Privacy-preserving insights into real-world ai use A Tamkin, M McCain, K Handa, E Durmus, L Lovitt, A Rathi, S Huang, ... arXiv preprint arXiv:2412.13678, 2024 | 48 | 2024 |
| Simplifying GPS data for map building and distance calculation S Cui, TD Nguyen, TR Sumers, M Yu, X Zhang US Patent 9,939,276, 2018 | 44 | 2018 |
| How do Large Language Models Navigate Conflicts between Honesty and Helpfulness? R Liu*, TR Sumers*, I Dasgupta, TL Griffiths ICML, 2024 | 42 | 2024 |
| How to talk so AI will learn: Instructions, descriptions, and autonomy T Sumers, R Hawkins, MK Ho, T Griffiths, D Hadfield-Menell Advances in neural information processing systems 35, 34762-34775, 2022 | 41* | 2022 |
| Distilling Internet-Scale Vision-Language Models into Embodied Agents T Sumers, K Marino, A Ahuja, R Fergus, I Dasgupta International Conference on Machine Learning, 2023 | 40 | 2023 |
| Show or tell? Exploring when (and why) teaching with language outperforms demonstration TR Sumers, MK Ho, RD Hawkins, TL Griffiths Cognition 232, 105326, 2023 | 34* | 2023 |
| Pickup location selection and augmented reality navigation J Badalamenti, J Inch, CM Sanchez, TR Sumers US Patent 10,508,925, 2019 | 34 | 2019 |
| Network computer system for analyzing driving actions of drivers on road segments of a geographic region TR Sumers US Patent 10,297,148, 2019 | 31 | 2019 |
| Scaling monosemanticity: Extracting interpretable features from claude 3 sonnet, 2024 A Templeton, T Conerly, J Marcus, J Lindsey, T Bricken, B Chen, ... URL https://transformer-circuits. pub/2024/scaling-monosemanticity 1, 2024 | 27 | 2024 |
| Trip termination determination for on-demand transport K Brinig, M Ioffe, B Layton, T Sumers, MW Kadous US Patent 10,672,198, 2020 | 27 | 2020 |
| Cascaded boosted predictive models D Purdy, L Chen, TR Sumers US Patent 11,138,524, 2021 | 26 | 2021 |
| Augmented reality assisted pickup J Badalamenti, J Inch, CM Sanchez, TR Sumers US Patent 10,423,834, 2019 | 24 | 2019 |
Thomas L. GriffithsProfessor of Psychology and Computer Science, Princeton UniversityVerified email at princeton.edu
