InterpretabilityResearch

A Mathematical Framework for Transformer Circuits

Dec 22, 2021
Read Paper


Related content

A global workspace in language models

New interpretability research reveals an emergent mental workspace in Claude that holds internal thoughts that don’t appear in the model’s output.

Read more

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 more

Project 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 more