Pith. sign in

REVIEW 2 cited by

Evolution of SAE Features Across Layers in LLMs

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.08869 v2 pith:WYOKPUYO submitted 2024-10-11 cs.LG

Daniel Balcells , Benjamin Lerner , Michael Oesterle , Ediz Ucar , Stefan Heimersheim This is my paper · ORCID
classification cs.LG
keywords featureslayersacrosslayerprevioussomeadjacentamount
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Sparse Autoencoders for transformer-based language models are typically defined independently per layer. In this work we analyze statistical relationships between features in adjacent layers to understand how features evolve through a forward pass. We provide a graph visualization interface for features and their most similar next-layer neighbors (https://stefanhex.com/spar-2024/feature-browser/), and build communities of related features across layers. We find that a considerable amount of features are passed through from a previous layer, some features can be expressed as quasi-boolean combinations of previous features, and some features become more specialized in later layers.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects

    cs.LG 2026-07 conditional novelty 6.0 of 10

    A single-token feature's causal necessity under zero-ablation depends on which SAE family found it: GemmaScope and BatchTopK features stay causally anchored while LlamaScope features are locally redundant.

  2. Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

    cs.LG 2025-02 conditional novelty 5.0 of 10

    Cosine similarity between sparse autoencoder features across layers and modules builds flow graphs that explain feature evolution and enable multi-layer steering of language model generation.

Pith tools