| Interpretability in the wild: a circuit for indirect object identification in gpt-2 small K Wang, A Variengien, A Conmy, B Shlegeris, J Steinhardt arXiv preprint arXiv:2211.00593, 2022 | 171 | 2022 |
| How does gpt-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model M Hanna, O Liu, A Variengien Advances in Neural Information Processing Systems 36, 2024 | 43* | 2024 |
| Towards self-organized control: Using neural cellular automata to robustly control a cart-pole agent A Variengien, S Nichele, T Glover, S Pontes-Filho arXiv preprint arXiv:2106.15240, 2021 | 33* | 2021 |
| A journey in ESN and LSTM visualisations on a language task A Variengien, X Hinaut arXiv preprint arXiv:2012.01748, 2020 | 13 | 2020 |
| Look Before You Leap: A Universal Emergent Decomposition of Retrieval Tasks in Language Models A Variengien, E Winsor arXiv preprint arXiv:2312.10091, 2023 | 2 | 2023 |
| Recurrent Neural Networks Models for Developmental Language Acquisition: Reservoirs Outperform LSTMs X Hinaut, A Variengien SNL 2020-12th Annual Meeting of the Society for the Neurobiology of Language, 2020 | | 2020 |
Arthur ConmyGoogle DeepMindVerified email at google.com
