2 citations · 2 across the 3 of their papers we have counts for
3 papers
Modular addition without black-boxes: Compressing explanations of MLPs that compute numerical integration
Chun Hei Yip, Rajashree Agrawal, Lawrence Chan +1
The goal of mechanistic interpretability is discovering simpler, low-rank algorithms implemented by models. While we can compress activations into features, compressing nonlinear f…
Compact Proofs of Model Performance via Mechanistic Interpretability
Jason Gross, Rajashree Agrawal, Thomas Kwa +5
We propose using mechanistic interpretability -- techniques for reverse engineering model weights into human-interpretable algorithms -- to derive and compactly prove formal guaran…
Towards a Scalable Proof Engine: A Performant Prototype Rewriting Primitive for Coq
Jason Gross, Andres Erbsen, Jade Philipoom +2
We address the challenges of scaling verification efforts to match the increasing complexity and size of systems. We propose a research agenda aimed at building a performant proof…