Pith. sign in

REVIEW 6 cited by

Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT

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 2402.12201 v1 pith:MJIY3TJC submitted 2024-02-19 cs.LG

Zhengfu He , Xuyang Ge , Qiong Tang , Tianxiang Sun , Qinyuan Cheng , Xipeng Qiu This is my paper · ORCID
classification cs.LG
keywords dictionaryfeaturesframeworkattentioncircuitcircuitsdiscoveryhuman-understandable
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Sparse dictionary learning has been a rapidly growing technique in mechanistic interpretability to attack superposition and extract more human-understandable features from model activations. We ask a further question based on the extracted more monosemantic features: How do we recognize circuits connecting the enormous amount of dictionary features? We propose a circuit discovery framework alternative to activation patching. Our framework suffers less from out-of-distribution and proves to be more efficient in terms of asymptotic complexity. The basic unit in our framework is dictionary features decomposed from all modules writing to the residual stream, including embedding, attention output and MLP output. Starting from any logit, dictionary feature or attention score, we manage to trace down to lower-level dictionary features of all tokens and compute their contribution to these more interpretable and local model behaviors. We dig in a small transformer trained on a synthetic task named Othello and find a number of human-understandable fine-grained circuits inside of it.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. Transformers Use Causal World Models in Maze-Solving Tasks

    cs.LG 2024-12 conditional novelty 7.0 of 10

    Maze-solving transformers store a causal, steerable map of maze connections in sparse features, and activating these features is more effective than removing them.

  2. Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition

    cs.LG 2025-04 conditional novelty 6.0 of 10

    Lorsa replaces an MHSA layer with thousands of sparsely activated rank-1 attention heads and shows these heads recover known behaviors like induction heads plus new arithmetic and thematic units.

  3. Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words

    cs.CL 2025-01 conditional novelty 6.0 of 10

    PS-Eval, a Word-in-Context-based benchmark, shows that SAEs optimized for MSE-L0 do not necessarily extract better word-meaning features, and that separation improves in deeper layers and attention outputs.

  4. EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification

    cs.LG 2025-02 conditional novelty 5.0 of 10

    EAP-GP adapts the integration path in edge attribution patching to avoid gradient saturation, improving circuit faithfulness on GPT-2 models.

  5. NEAT: Concept driven Neuron Attribution in LLMs

    cs.CL 2025-08 reject novelty 4.0 of 10

    NEAT identifies concept neurons by feeding a single mean hidden-state vector through the model and ranking neurons by their effect on concept-word probabilities.

  6. Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning

    cs.AI 2025-02 reject novelty 4.0 of 10

    SICAF traces per-token self-influence inside extracted circuits to map GPT-2's reasoning on the IOI task.

Pith tools