| Progress measures for grokking via mechanistic interpretability N Nanda, L Chan, T Lieberum, J Smith, J Steinhardt arXiv preprint arXiv:2301.05217, 2023 | 354 | 2023 |
| Does circuit analysis interpretability scale? evidence from multiple choice capabilities in chinchilla T Lieberum, M Rahtz, J Kramár, N Nanda, G Irving, R Shah, V Mikulik arXiv preprint arXiv:2307.09458, 2023 | 67 | 2023 |
| Gemma scope: Open sparse autoencoders everywhere all at once on gemma 2 T Lieberum, S Rajamanoharan, A Conmy, L Smith, N Sonnerat, V Varma, ... arXiv preprint arXiv:2408.05147, 2024 | 62 | 2024 |
| Improving dictionary learning with gated sparse autoencoders S Rajamanoharan, A Conmy, L Smith, T Lieberum, V Varma, J Kramár, ... arXiv preprint arXiv:2404.16014, 2024 | 47 | 2024 |
| Jumping ahead: Improving reconstruction fidelity with jumprelu sparse autoencoders S Rajamanoharan, T Lieberum, N Sonnerat, A Conmy, V Varma, J Kramár, ... arXiv preprint arXiv:2407.14435, 2024 | 35 | 2024 |
| Atp*: An efficient and scalable method for localizing llm behaviour to components J Kramár, T Lieberum, R Shah, N Nanda arXiv preprint arXiv:2403.00745, 2024 | 27 | 2024 |
| Progress measures for grokking via mechanistic interpretability, 2023 N Nanda, L Chan, T Lieberum, J Smith, J Steinhardt URL https://arxiv. org/abs/2301.05217, 2023 | 26 | 2023 |
| Seliem El-Sayed, Sasha Brown, Anca Dragan, Rohin Shah, Allan Dafoe, and Toby Shevlane M Phuong, M Aitchison, E Catt, S Cogan, A Kaskasoli, V Krakovna, ... Evaluating frontier models for dangerous capabilities, 2024 | 16 | 2024 |
| Does circuit analysis interpretability scale T Lieberum, M Rahtz, J Kramár, N Nanda, G Irving, R Shah, V Mikulik Evidence from multiple choice capabilities in Chinchilla, 2023 | 13 | 2023 |
| Retrospective on the 2021 minerl BASALT competition on learning from human feedback R Shah, SH Wang, C Wild, S Milani, A Kanervisto, VG Goecks, ... NeurIPS 2021 Competitions and Demonstrations Track, 259-272, 2022 | 9 | 2022 |
| Does circuit analysis interpretability scale? evidence from multiple choice capabilities in chinchilla, 2023 T Lieberum, M Rahtz, J Kramár, N Nanda, G Irving, R Shah, V Mikulik URL https://arxiv. org/abs/2307.09458, 0 | 7 | |
| Improving sparse decomposition of language model activations with gated sparse autoencoders S Rajamanoharan, A Conmy, L Smith, T Lieberum, V Varma, J Kramar, ... Advances in Neural Information Processing Systems 37, 775-818, 2025 | 2 | 2025 |
| Retrospective on the 2021 BASALT competition on learning from human feedback R Shah, SH Wang, C Wild, S Milani, A Kanervisto, VG Goecks, ... arXiv preprint arXiv:2204.07123, 2022 | 2 | 2022 |
| Progress measures for grokking via mechanistic interpretability, Oct. 2023 N Nanda, L Chan, T Lieberum, J Smith, J Steinhardt URL http://arxiv. org/abs/2301.05217, 0 | 2 | |
| Replication: Fairness without demographics through Adversarially Reweighted Learning E Jenner, T Lieberum, FP Nolte, N Rutsch | | |