| Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small KR Wang, A Variengien, A Conmy, B Shlegeris, J Steinhardt ICLR 2023, 2022 | 455 | 2022 |
| Towards Automated Circuit Discovery for Mechanistic Interpretability A Conmy, AN Mavor-Parker, A Lynch, S Heimersheim, A Garriga-Alonso NeurIPS 2023 Spotlight, 2023 | 255 | 2023 |
| Stealing Part of a Production Language Model N Carlini, D Paleka, KD Dvijotham, T Steinke, J Hayase, AF Cooper, ... ICML 2024 Best Paper, 2024 | 78 | 2024 |
| Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 T Lieberum, S Rajamanoharan, A Conmy, L Smith, N Sonnerat, V Varma, ... BlackboxNLP 2024 Oral, 2024 | 63 | 2024 |
| Improving Dictionary Learning with Gated Sparse Autoencoders S Rajamanoharan, A Conmy, L Smith, T Lieberum, V Varma, J Kramár, ... NeurIPS 2024, 2024 | 52 | 2024 |
| Attribution Patching Outperforms Automated Circuit Discovery A Syed, C Rager, A Conmy BlackboxNLP 2024, 2023 | 51 | 2023 |
| Copy Suppression: Comprehensively Understanding a Motif in Language Model Attention Heads CS McDougall, A Conmy, C Rushing, T McGrath, N Nanda BlackboxNLP 2024, 2023 | 38* | 2023 |
| 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 |
| Successor Heads: Recurring, Interpretable Attention Heads In The Wild R Gould, E Ong, G Ogden, A Conmy ICLR 2024, 2023 | 35 | 2023 |
| Interpreting Attention Layer Outputs with Sparse Autoencoders C Kissane, R Krzyzanowski, JI Bloom, A Conmy, N Nanda ICML 2024 Mechanistic Interpretability Workshop Spotlight, 2024 | 29* | 2024 |
| Improving Steering Vectors by Targeting Sparse Autoencoder Features S Chalnev, M Siu, A Conmy arXiv preprint arXiv:2411.02193, 2024 | 9* | 2024 |
| StyleGAN-induced Data-Driven Regularization for Inverse Problems A Conmy, S Mukherjee, CB Schönlieb IEEE ICASSP 2022, 2022 | 6 | 2022 |
| SAEs (Usually) Transfer Between Base and Chat Models C Kissane, R Krzyzanowski, A Conmy, N Nanda alignmentforum.org/posts/fmwk6qxrpW8d4jvbd, 2024 | 5 | 2024 |
| Activation Steering with SAEs A Conmy, N Nanda alignmentforum.org/posts/C5KAZQib3bzzpeyrg#Activation_Steering_with_SAEs, 2024 | 5 | 2024 |
| Self-explaining SAE Features D Kharlapenko, S Shabalin, N Nanda, A Conmy alignmentforum.org/posts/self-explaining-sae-features, 2024 | 4* | 2024 |
| Applying Sparse Autoencoders to Unlearn Knowledge in Language Models E Farrell, YT Lau, A Conmy Safe Generative AI Workshop at NeurIPS 2024, 2024 | 4 | 2024 |
| Open Problems in Mechanistic Interpretability L Sharkey, B Chughtai, J Batson, J Lindsey, J Wu, L Bushnaq, ... arXiv preprint arXiv:2501.16496, 2025 | 3 | 2025 |
| SAEs are Highly Dataset Dependent: a case study on the Refusal Direction C Kissane, R Krzyzanowski, N Nanda, A Conmy Alignment Forum, 2024 | 3 | 2024 |
| SAEBench: A Comprehensive Benchmark for Sparse Autoencoders A Karvonen, C Rager, J Lin, C Tigges, J Bloom, D Chanin, YT Lau, ... https://www.neuronpedia.org/sae-bench/info, 2025 | 2* | 2025 |
| Progress Update #1 from the GDM Mech Interp Team N Nanda, A Conmy, L Smith, S Rajamanoharan, T Lieberum, J Kramár, ... alignmentforum.org/posts/C5KAZQib3bzzpeyrg, 2024 | 2* | 2024 |
Neel NandaMechanistic Interpretability Team Lead, Google DeepMindAdresă de e-mail confirmată pe deepmind.com