Arthur Conmy
Anthropic Member of Technical Staff; former Google DeepMind senior research engineer; ACDC first author
Arthur Conmy is a Member of Technical Staff at Anthropic; Conmy's site describes the role as working on aligning upcoming models as they are trained. From 2023 to 2026 Conmy was a Senior Research Engineer at Google DeepMind, working on post-training for Gemini and on interpretability tools including Gemma Scope, sparse autoencoders, probes, and model diffing. Earlier work on circuits includes first authorship of ACDC, a method for automated circuit discovery, and co-authorship of the indirect object identification circuit study in GPT-2 small.12354
Work
Towards Automated Circuit Discovery for Mechanistic Interpretability (ACDC) (external site: arxiv.org)Published research
First author of the 2023 paper, which systematizes the mechanistic interpretability workflow and automates the step of identifying the circuit of model components responsible for a behavior.31
Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 (external site: arxiv.org)Published research
Co-author of the 2024 Google DeepMind report introducing an open suite of JumpReLU sparse autoencoders trained on Gemma 2 models; Conmy's site lists Gemma Scope 1 and 2 among the Google DeepMind work.41
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small (external site: arxiv.org)Published research
Co-author of the 2022 paper explaining how GPT-2 small performs indirect object identification in terms of groups of attention heads.51
Earlier roles
- Senior Research Engineer (2023–2026), Google DeepMind1
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.