Skip to main content

A Mathematical Framework for Transformer Circuits

Published
Dec 22, 2021
Team
Interpretability
Topics
- Interpretability
- Alignment

Related articles

Interpretability
Oct 5, 2023
Towards monosemanticity: Decomposing language models with dictionary learning

Our mission

Our mission is to help humankind chart a safe course through the evolution of intelligence and open new frontiers of discovery. Through research, policy, and the development of Claude, Anthropic works to navigate the transition to that better possible future.

Log in

Claude.ai
Claude console

© 2026 Anthropic PBC