Publication
Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?
Nils Grandien; David Steinmann; Felix Friedrich; Kristian Kersting
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2606.22994, Pages 1-21, arXiv, 2026.
Abstract
Sparse autoencoders (SAEs) have become an important tool for unsupervised
concept discovery in large models. To make the resulting feature spaces more
interpretable and manageable, recent approaches have begun imposing hierarchical
structure, either explicitly or as an implicit effect of training constraints, yet rigorous
comparison remains difficult. There are no agreed-upon requirements for what a
meaningful feature hierarchy should satisfy, and evaluation has largely relied on
qualitative illustrations with fragmented quantitative protocols. To address this,
we derive a set of key requirements for generalization/specialization hierarchies in
unsupervised concept discovery, drawing on semantic net and taxonomy research
alongside recent SAE work, and use them to derive a concrete evaluation protocol.
Applying this protocol to current SAE approaches trained on visual data, we
find that while feature spaces generally provide a basis for sensible hierarchies,
establishing good hierarchical structure remains challenging. In particular, feature
absorption, both in its well-known hard form and in a continuous, soft form,
systematically compromises hierarchy quality, pointing to a fundamental tension
that future approaches will need to navigate.1