Extracting Concepts from GPT-4
Free while signed in. Answers cite the passages they came from.
Paper preview
The curator’s take
proposes a new scalable method based on sparse autoencoders to extract around 16 million interpretable patterns from GPT-4; the method demonstrates predictable scaling and is more efficient than previous techniques.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack