Mechanistic Interpretability for AI Safety -- A Review
Leonard Bereska, Efstratios Gavves
Who it is from
- University of Amsterdamaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- The effects of data quality on machine learning performance on tabular dataUniversity of Amsterdam · 693 citations
- NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMUniversity of Amsterdam · 294 citations
- VISA: Reasoning Video Object Segmentation via Large Language ModelsUniversity of Amsterdam · 236 citations