Attribution Patching Outperforms Automated Circuit Discovery

Attribution Patching Outperforms Automated Circuit Discovery Aaquib Syed author Can Rager author Arthur Conmy author 2024-11 text Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP Yonatan Belinkov editor Najoung Kim editor Jaap Jumelet editor Hosein Mohebbi editor Aaron Mueller editor Hanjie Chen editor Association for Computational Linguistics Miami, Florida, US conference publication syed-etal-2024-attribution 10.18653/v1/2024.blackboxnlp-1.25 https://aclanthology.org/2024.blackboxnlp-1.25/ 2024-11 407 416