The letter

One letter a week, in your inbox.

The signal of the week, what shipped, what to try, and the editor's note. No tracking, no ads, nothing else.

We keep your address, your language and the date you joined, nothing else. Every letter has a one-click unsubscribe link that deletes the record.

← Accept All   Archive
Transformer CircuitsResearch

Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations

May 7

We train Claude to translate its internal state into natural language.

paper
Read at Transformer Circuits ↗

More from Transformer Circuits on Accept All.