Scholar
Thomas Kwa
Google Scholar ID: ufMe6I8AAAAJ
Unknown affiliation
AI safety
mechanistic interpretability
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
98
H-index
4
i10-index
1
Publications
10
Co-authors
0
Publications
4 items
HCAST: Human-Calibrated Autonomy Software Tasks
2025
Cited
0
Measuring AI Ability to Complete Long Tasks
2025
Cited
0
InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques
Neural Information Processing Systems · 2024
Cited
4
Compact Proofs of Model Performance via Mechanistic Interpretability
arXiv.org · 2024
Cited
4
