Neurips2025_mi
We have two papers accepted to the Mechanistic Interpretability workshop at NeurIPS 2025! One is about equivariant sparse autoencoders, the other is about causal abstraction as a framework for faithfulness.
We have two papers accepted to the Mechanistic Interpretability workshop at NeurIPS 2025! One is about equivariant sparse autoencoders, the other is about causal abstraction as a framework for faithfulness.