Using dictionary learning features as classifiers
At the link above, we report some developing work from the Anthropic interpretability team on developing feature-based classifiers, which might be of interest to researchers working actively in this space. We'd ask you to treat these results like those of a colleague sharing some thoughts or preliminary experiments for a few minutes at a lab meeting, rather than a mature paper.
Related content
Anthropic Economic Index report: Cadences
In our latest Economic Index report, we sample hourly for the first time to ask: When do people come to Claude? What do they produce with it? And how do they perceive AI's impact on their work?
Read moreProject Fetch: Phase two
We report results from our latest test of whether Claude can help Anthropic employees perform sophisticated robotics tasks. We found that Claude Opus 4.7, operating without human assistance, was about 20 times faster than the fastest human team at all tasks completed by participants less than a year ago.
Read moreAgentic coding and persistent returns to expertise
This report provides evidence on how Claude Code is used in practice, based on a privacy-preserving analysis of around 400,000 interactive sessions from around 235,000 people between October 2025 and April 2026.
Read more