method · first seen 14 Nov 2026
activation explanation
Techniques for producing human-readable descriptions of what information a language model's internal activations encode.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Evaluating and Improving Natural Language AutoencodersPapers · 14 Nov 2026 · Marco Bazzani, Dan Mossing
Latest sources
- Evaluating and Improving Natural Language AutoencodersPapers · 14 Nov 2026 · Marco Bazzani, Dan Mossing