Follow
Arthur Conmy
Arthur Conmy
Google DeepMind
Verified email at google.com - Homepage
Title
Cited by
Cited by
Year
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small
K Wang, A Variengien, A Conmy, B Shlegeris, J Steinhardt
ICLR 2023, 2022
2442022
Towards Automated Circuit Discovery for Mechanistic Interpretability
A Conmy, AN Mavor-Parker, A Lynch, S Heimersheim, A Garriga-Alonso
NeurIPS 2023 Spotlight, 2023
1182023
Stealing Part of a Production Language Model
N Carlini, D Paleka, KD Dvijotham, T Steinke, J Hayase, AF Cooper, ...
ICML 2024 Best Paper, 2024
212024
Attribution Patching Outperforms Automated Circuit Discovery
A Syed, C Rager, A Conmy
NeurIPS 2023 Workshop (Attributing Model Behavior at Scale), 2023
182023
Copy Suppression: Comprehensively Understanding an Attention Head
C McDougall, A Conmy, C Rushing, T McGrath, N Nanda
NeurIPS 2023 Workshop (Attributing Model Behavior at Scale), 2023
162023
Successor Heads: Recurring, Interpretable Attention Heads In The Wild
R Gould, E Ong, G Ogden, A Conmy
ICLR 2024, 2023
112023
Improving Dictionary Learning with Gated Sparse Autoencoders
S Rajamanoharan, A Conmy, L Smith, T Lieberum, V Varma, J Kramár, ...
ICML 2024 Mechanistic Interpretability Workshop, 2024
10*2024
Interpreting Attention Layer Outputs with Sparse Autoencoders
C Kissane, R Krzyzanowski, JI Bloom, A Conmy, N Nanda
ICML 2024 Mechanistic Interpretability Workshop Spotlight, 2024
9*2024
StyleGAN-induced Data-Driven Regularization for Inverse Problems
A Conmy, S Mukherjee, CB Schönlieb
IEEE ICASSP 2022, 2022
52022
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
2024
Activation Steering with SAEs
A Conmy, N Nanda
www.alignmentforum.org/posts/C5KAZQib3bzzpeyrg, 2024
2024
The system can't perform the operation now. Try again later.
Articles 1–11