Interpretability

Using dictionary learning features as classifiers

Oct 16, 2024
Read Transformer Circuits

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

Discovering cryptographic weaknesses with Claude

cryptographic algorithms. The first attack significantly weakens HAWK, a digital signature scheme that was built for a future world where quantum computers are able to break existing standards. The second identifies a new way to attack round-reduced AES, the most widely used symmetric cipher.

Read more

Project Pilot: Can AI control a drone?

Working with Andon Labs, we’ve developed a new series of evaluations that assess AI models’ ability to use a flying drone, culminating in a new benchmark: Drone-Bench.

Read more

How Canada uses Claude: Findings from the Anthropic Economic Index

Read more