Pith. sign in

REVIEW 16 cited by

Automatically Interpreting Millions of Features in Large Language Models

Not yet reviewed by Pith; the record is open.

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 2410.13928 v3 pith:3MYT5KLZ submitted 2024-10-17 cs.LG cs.CL

classification cs.LGcs.CL
keywords explanationssaesfeaturesneuronstechniquestrainedactivationsavailable
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

While the activations of neurons in deep neural networks usually do not have a simple human-understandable interpretation, sparse autoencoders (SAEs) can be used to transform these activations into a higher-dimensional latent space which may be more easily interpretable. However, these SAEs can have millions of distinct latent features, making it infeasible for humans to manually interpret each one. In this work, we build an open-source automated pipeline to generate and evaluate natural language explanations for SAE features using LLMs. We test our framework on SAEs of varying sizes, activation functions, and losses, trained on two different open-weight LLMs. We introduce five new techniques to score the quality of explanations that are cheaper to run than the previous state of the art. One of these techniques, intervention scoring, evaluates the interpretability of the effects of intervening on a feature, which we find explains features that are not recalled by existing methods. We propose guidelines for generating better explanations that remain valid for a broader set of activating contexts, and discuss pitfalls with existing scoring techniques. We use our explanations to measure the semantic similarity of independently trained SAEs, and find that SAEs trained on nearby layers of the residual stream are highly similar. Our large-scale analysis confirms that SAE latents are indeed much more interpretable than neurons, even when neurons are sparsified using top-$k$ postprocessing. Our code is available at https://github.com/EleutherAI/sae-auto-interp, and our explanations are available at https://huggingface.co/datasets/EleutherAI/auto_interp_explanations.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 16 Pith papers

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

  1. Verbalizable Representations Form a Global Workspace in Language Models

    cs.CL 2026-07 conditional novelty 7.0 of 10

    Language models represent their current reasoning in a small, readable set of verbalizable vectors (the J-space) that functions like a global workspace.

  2. Making Interpretable Discoveries from Unstructured Data: A High-Dimensional Multiple Hypothesis Testing Approach

    econ.EM 2025-11 unverdicted novelty 7.0 of 10

    A new framework combines AI-derived concept embeddings with high-dimensional selective inference to enable statistically principled, interpretable discovery from unstructured data in empirical economics.

  3. 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.

  4. ChronoLens: Measuring Language Change Across Time, Languages, and Linguistic Levels

    cs.CL 2026-08 conditional novelty 6.0 of 10

    ChronoLens uses feature-aligned crosscoders to show that historical language change has comparable magnitude across linguistic levels within a language, but divergent timing and direction across five parliamentary languages.

  5. LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering

    cs.CL 2026-04 conditional novelty 6.0 of 10

    Language-specific sparse autoencoder features can be identified from monolingual data alone by filtering out features that also activate on random-token sequences, and steering with these features improves language control.

  6. Visual Persuasion: What Influences Decisions of Vision-Language Models?

    cs.CV 2026-02 conditional novelty 6.0 of 10

    Naturalistic edits to background, lighting, and staging systematically shift the choices of frontier vision-language models, and a new optimization-plus-interpretation framework (CVPO) discovers and explains the visua...

  7. Prototype Transformer: Towards Language Model Architectures Interpretable by Design

    cs.AI 2026-02 conditional novelty 6.0 of 10

    ProtoT is an autoregressive language model whose attention is replaced by learned prototype channels that are claimed to capture nameable concepts and allow targeted edits, at linear sequence cost but with slightly lo...

  8. Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders

    cs.CL 2025-07 conditional novelty 6.0 of 10

    MTMs replace word counts with SAE features, producing more abstract topics and enabling topic steering, and outperform word-based baselines in LLM and human pairwise evaluations.

  9. Teach Old SAEs New Domain Tricks with Boosting

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Training a small secondary sparse autoencoder on the reconstruction error of a pretrained SAE improves domain-specific reconstruction and language-model perplexity without hurting general performance.

  10. Insights into a radiology-specialised multimodal large language model with sparse autoencoders

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Applying Matryoshka sparse autoencoders to a radiology-specialised multimodal LLM reveals a minority of interpretable clinical features, while steering them produces unreliable and often off-target report changes.

  11. Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A position paper proposing feature consistency, measured by PW-MCC, as a core SAE evaluation criterion, with evidence that TopK SAEs achieve high consistency on LLM activations.

  12. Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models

    cs.LG 2025-05 conditional novelty 6.0 of 10

    ITDA dictionaries, built greedily from poorly reconstructed activations and decomposed by matching pursuit, match some SAE reconstruction performance at 100x lower training cost and enable SOTA cross-model layer simil...

  13. Distribution-Aware Feature Selection for SAEs

    cs.LG 2025-08 conditional novelty 5.0 of 10

    Sampled-SAE pre-selects a candidate pool of features using batch-level norms or entropy before batch top-K, creating a tunable family that trades reconstruction fidelity for improved probing and reduced absorption on ...

  14. Evaluating SAE interpretability without explanations

    cs.LG 2025-07 conditional novelty 5.0 of 10

    SAE latent interpretability can be scored directly from activation examples via intruder detection and embedding clustering, with LLM scores correlating strongly with human scores.

  15. Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy

    cs.LG 2025-05 conditional novelty 5.0 of 10

    HierarchicalTopK trains a single sparse autoencoder that reconstructs transformer activations well at many sparsity levels, matching or beating separate per-level models.

  16. CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs

    cs.LG 2026-03 conditional novelty 4.0 of 10

    CLT-Forge packages feature-sharded CLT training, compressed activation caching, automated interpretability, Circuit-Tracer attribution graphs, and a Dash visualizer into a single open-source library.

Pith tools