arxiv:2605.01844
Lang Gao
·
AI & ML interests
Mechanistic Interpretability of AI
Recent Activity
updated a dataset 3 days ago
LangGao/pythia-160m-neuron-evolution published a dataset 4 days ago
LangGao/pythia-160m-neuron-evolution upvoted a paper about 1 month ago
Evaluate Bias without Manual Test Sets: A Concept Representation
Perspective for LLMs