Comment Comment by colah3 (Disclaimer: I work on interpretability at Anthropic.)I wanted to flag that this is an accessible blog post and that there's a link to the paper ( https://transformer-circuits.pub/2025/introspection/index.ht... ) at the top. The paper explores this in more detail and rigor. parent colah3 1 year ago
I wanted to flag that this is an accessible blog post and that there's a link to the paper ( https://transformer-circuits.pub/2025/introspection/index.ht... ) at the top. The paper explores this in more detail and rigor.