| Eliciting latent predictions from transformers with the tuned lens N Belrose, Z Furman, L Smith, D Halawi, I Ostrovsky, L McKinney, ... arXiv preprint arXiv:2303.08112, 2023 | 69 | 2023 |
| Leace: Perfect linear concept erasure in closed form N Belrose, D Schneider-Joseph, S Ravfogel, R Cotterell, E Raff, ... Advances in Neural Information Processing Systems 36, 2024 | 39 | 2024 |
| imitation: Clean imitation learning implementations A Gleave, M Taufeeque, J Rocamonde, E Jenner, SH Wang, S Toyer, ... arXiv preprint arXiv:2211.11972, 2022 | 27 | 2022 |
| Adversarial policies beat professional-level go ais TT Wang, A Gleave, N Belrose, T Tseng, MD Dennis, Y Duan, ... Deep Reinforcement Learning Workshop NeurIPS 2022, 2022 | 26 | 2022 |
| Adversarial policies beat superhuman go AIs TT Wang, A Gleave, T Tseng, K Pelrine, N Belrose, J Miller, MD Dennis, ... International Conference on Machine Learning, 35655-35739, 2023 | 14 | 2023 |
| Neural Networks Learn Statistics of Increasing Complexity N Belrose, Q Pope, L Quirke, A Mallen, X Fern arXiv preprint arXiv:2402.04362, 2024 | 1 | 2024 |
| Eliciting Latent Knowledge from Quirky Language Models A Mallen, N Belrose arXiv preprint arXiv:2312.01037, 2023 | 1 | 2023 |
| Quantitative and Automated Breast Arterial Calcification Score is Associated With Traditional Cardiovascular Risk Factors TS Allen, QM Bui, AV Sykes, N Belrose, N Nerlekar, R Mantey, J Wang, ... Circulation 146 (Suppl_1), A11669-A11669, 2022 | 1 | 2022 |
| Does Transformer Interpretability Transfer to RNNs? G Paulo, T Marshall, N Belrose arXiv preprint arXiv:2404.05971, 2024 | | 2024 |
| Abstract P522: Breast Arterial Calcification Predicts Heart Failure Across Racial and Ethnic Groups TS Allen, GM Petersen, R Mantey, J Wang, N Nerlekar, N Belrose, ... Circulation 147 (Suppl_1), AP522-AP522, 2023 | | 2023 |
| Association of Breast Arterial Calcification With Clinical Outcomes and Mortality QM Bui, AV Sykes, T Allen, N Belrose, N Nerlekar, R Mantey, J Wang, ... Circulation 146 (Suppl_1), A11647-A11647, 2022 | | 2022 |
| High Performance of Artificial Intelligence-Based Model for Scoring Breast Arterial Calcification on Mammograms N Nerlekar, V Goel, C Yeong, E Spear, W Cameron, R Mantey, N Belrose, ... Circulation 146 (Suppl_1), A14573-A14573, 2022 | | 2022 |
| How Age Affects the Association of Breast Arterial Calcification With Clinical Outcomes and Mortality AV Sykes, QM Bui, TS Allen, N Belrose, N Nerlekar, R Mantey, J Wang, ... Circulation 146 (Suppl_1), A11707-A11707, 2022 | | 2022 |
Stuart RussellProfessor of Computer Science, University of California, BerkeleyVerified email at cs.berkeley.edu
