TaxoSAE: Rethinking Sparse Autoencoders through Taxonomic Logic
arXiv:2610.31894v1 Announce Type: new Abstract: Recent Sparse Autoencoders (SAEs) decompose the representations of large language models (LLMs) into interpretable features, enabling precise readout and control of encoded knowledge. However, existing SAEs treat each feature as a standalone unit, whe…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-26 04:00 · arXiv cs.CL
TaxoSAE: Rethinking Sparse Autoencoders through Taxonomic Logic