#machine learning
Dec 2025
AlignSAE: Concept-Aligned Sparse Autoencoders
AlignSAE is introduced, a method that aligns SAE features with a predefined ontology through a "pre-train, then post-train"curriculum and achieves disentanglement improvements of $9$--$\infty\times$ over standard SAEs, and further supports multi-hop reasoning and a mechanistic probe of grokking-like generalization dyna...
Minglai Yang, Xin-Yu Guo, Zheng-Liang Shi et al.
· arXiv.org · 4 citations