Pith. sign in

REVIEW 5 cited by

Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning

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 2405.12241 v2 pith:NAQI2LAU submitted 2024-05-17 cs.LG cs.AI

Dan Braun , Jordan Taylor , Nicholas Goldowsky-Dill , Lee Sharkey This is my paper · ORCID
classification cs.LGcs.AI
keywords featuressaesnetworkdictionarysparsefunctionallyimportantlearning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Identifying the features learned by neural networks is a core challenge in mechanistic interpretability. Sparse autoencoders (SAEs), which learn a sparse, overcomplete dictionary that reconstructs a network's internal activations, have been used to identify these features. However, SAEs may learn more about the structure of the datatset than the computational structure of the network. There is therefore only indirect reason to believe that the directions found in these dictionaries are functionally important to the network. We propose end-to-end (e2e) sparse dictionary learning, a method for training SAEs that ensures the features learned are functionally important by minimizing the KL divergence between the output distributions of the original model and the model with SAE activations inserted. Compared to standard SAEs, e2e SAEs offer a Pareto improvement: They explain more network performance, require fewer total features, and require fewer simultaneously active features per datapoint, all with no cost to interpretability. We explore geometric and qualitative differences between e2e SAE features and standard SAE features. E2e dictionary learning brings us closer to methods that can explain network behavior concisely and accurately. We release our library for training e2e SAEs and reproducing our analysis at https://github.com/ApolloResearch/e2e_sae

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Training, Reading, and Editing Legible Transformers

    cs.LG 2026-07 conditional novelty 6.5 of 10

    A variance-floor objective plus learned operator gates produce an end-to-end legible transformer whose crisp units are 50–184× more local to edit and can be reshaped from fan-out to fan-in circuits without quality loss.

  2. Low-Rank Adapting Models for Sparse Autoencoders

    cs.LG 2025-01 conditional novelty 6.0 of 10

    LoRA fine-tuning of the language model around a fixed SAE reduces the SAE-insertion loss gap by 30-55% and matches end-to-end SAEs 2-20x faster.

  3. Cross-seed explainability using Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoders

    cs.CL 2026-07 conditional novelty 5.5 of 10

    Procrustes-conditioned joint End-to-end Top-K SAEs recover more cross-seed universal features (r≥0.70) from independent BERT seeds than post-hoc alignment baselines on three NLP datasets.

  4. Stable and Steerable Sparse Autoencoders with Weight Regularization

    stat.ML 2026-03 conditional novelty 5.0 of 10

    L2 weight regularization in TopK SAEs increases cross-seed feature overlap and roughly doubles measured steering success on Pythia-70M, at the cost of collapsing most latents to zero.

  5. Discovering Chunks in Neural Embeddings for Interpretability

    cs.LG 2025-02 conditional novelty 5.0 of 10

    Recurring 'chunks' in neural embeddings can be extracted, predict input patterns, and be perturbed to steer a model's outputs.

Pith tools