نسخة أولية وصول مفتوح
When Trees Are Not Enough: Learning Mixed-Topology Feature Graphs with Adaptive Graph Sparse Autoencoders
Sparse autoencoders (SAEs) expose interpretable features in large language model activations, yet existing structured SAEs impose single-parent trees or forests, while post-hoc graphs permit multiple parents but neither guide feature learning nor ensure reliable relation recovery. We introduce the Adaptive Graph Sparse …