Insights on Crosscoder Model Diffing
ID: 00f0d0fc-b0bb-5635-bfbf-8cf92bcb22a8
STIX ID: report--00f0d0fc-b0bb-5635-bfbf-8cf92bcb22a8
Feed Name: Anthropic Research
This brief note references developing work by the Anthropic Interpretability team on Crosscoder Model Diffing, presenting preliminary experiments and observations intended as informal lab‑meeting style findings rather than a mature paper.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.