TaxoSAE: Rethinking Sparse Autoencoders through Taxonomic Logic

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, whereas real-world knowledge is often taxonomically organized.

As a result, readout carries no guarantee of taxonomic consistency, and control lacks the granularity to specify the scope of an edit.

We propose TaxoSAE, which explicitly encodes taxonomical information, built on is-a (hypernym-hyponym) relations, into the SAE feature space.

TaxoSAE mirrors a taxonomy with a stack of SAEs, one per taxonomy level, and introduces a taxonomic alignment loss that trains each concept to be active whenever one of its hyponyms is.

On two factual QA taxonomies, one over biographical relations and one over animals, TaxoSAE enables (1) more accurate readout through the taxonomy with concentrated activations, e.g., +31.3 points in reading out the hypernyms of abstract concepts never queried in training; (2) more precise control, with +25.5 points in swap success, while suppressing a concept removes only its own answers (0-2% accuracy vs. 91-100% on other concepts); and, more importantly, (3) readout of unseen concepts through their hypernyms, with up to +37.9 points in hypernym readout accuracy.