Dense SAE Latents Are Features, Not Bugs

TL;DR

This paper investigates dense latents in sparse autoencoders for language models, revealing they are meaningful, functionally relevant features rather than mere artifacts or noise.

Contribution

It provides a systematic analysis of dense latents, showing they are intrinsic, meaningful, and evolve across layers, challenging the view that they are undesirable artifacts.

Findings

Dense latents form antipodal pairs reconstructing specific directions.

Ablating dense latents suppresses new dense features, indicating their intrinsic nature.

Dense features relate to position, context, POS, and output signals, evolving through model layers.

Abstract

Sparse autoencoders (SAEs) are designed to extract interpretable features from language models by enforcing a sparsity constraint. Ideally, training an SAE would yield latents that are both sparse and semantically meaningful. However, many SAE latents activate frequently (i.e., are \emph{dense}), raising concerns that they may be undesirable artifacts of the training procedure. In this work, we systematically investigate the geometry, function, and origin of dense latents and show that they are not only persistent but often reflect meaningful model representations. We first demonstrate that dense latents tend to form antipodal pairs that reconstruct specific directions in the residual stream, and that ablating their subspace suppresses the emergence of new dense features in retrained SAEs -- suggesting that high density features are an intrinsic property of the residual space. We then introduce a taxonomy of dense latents, identifying classes tied to position tracking, context binding, entropy regulation, letter-specific output signals, part-of-speech, and principal component reconstruction. Finally, we analyze how these features evolve across layers, revealing a shift from structural features in early layers, to semantic features in mid layers, and finally to output-oriented signals in the last layers of the model. Our findings indicate that dense latents serve functional roles in language model computation and should not be dismissed as training noise.