method · first seen 10 Oct 2026
automated interpretability
Using language models to generate and score natural-language explanations of neural network features.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Scoring Explanations Without Reading Them: Structural Shortcuts in Automated-Interpretability Evaluation DataPapers · 10 Oct 2026 · Xupeng Chen
- DECODE: Diagnosing Interpretability Failures in Automated Interpretation ProcessPapers · 13 Nov 2026 · Dohyun Kim, Jaeung Lee, Donghee Hong, Jaemin Jo
Latest sources
- DECODE: Diagnosing Interpretability Failures in Automated Interpretation ProcessPapers · 13 Nov 2026 · Dohyun Kim, Jaeung Lee, Donghee Hong, Jaemin Jo
- Scoring Explanations Without Reading Them: Structural Shortcuts in Automated-Interpretability Evaluation DataPapers · 10 Oct 2026 · Xupeng Chen