Neel Nanda MATS Applications Open (Due Aug 29)
"机械可解释性" 相关文章
Small foundational puzzle for causal theories of mechanistic interpretability
TT Self Study Journal # 1
Workshop: Interpretability in LLMs Using Geometric and Statistical Methods
Why I'm Moving from Mechanistic to Prosaic Interpretability
Why I'm Moving from Mechanistic to Empirical Interpretability
Google DeepMind has a new way to look inside an AI’s “mind”
Avoiding jailbreaks by discouraging their representation in activation space
A List of 45+ Mech Interp Project Ideas from Apollo Research’s Interpretability Team
Arrakis - A toolkit to conduct, track and visualize mechanistic interpretability experiments.
Mech Interp Lacks Good Paradigms
