Pith. sign in

REVIEW 5 cited by

Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors

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 2103.15949 v2 pith:NHE6LKZ2 submitted 2021-03-29 cs.CL cs.LG

classification cs.CLcs.LG
keywords transformervisualizationfactorslearningdictionaryknowledgelinearnetworks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Transformer networks have revolutionized NLP representation learning since they were introduced. Though a great effort has been made to explain the representation in transformers, it is widely recognized that our understanding is not sufficient. One important reason is that there lack enough visualization tools for detailed analysis. In this paper, we propose to use dictionary learning to open up these "black boxes" as linear superpositions of transformer factors. Through visualization, we demonstrate the hierarchical semantic structures captured by the transformer factors, e.g., word-level polysemy disambiguation, sentence-level pattern formation, and long-range dependency. While some of these patterns confirm the conventional prior linguistic knowledge, the rest are relatively unexpected, which may provide new insights. We hope this visualization tool can bring further knowledge and a better understanding of how transformer networks work. The code is available at https://github.com/zeyuyun1/TransformerVis

Discussion (0). Sign in 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. TimeSAE: Causal Sparse Decoding for Faithful Explanations of Black-Box Time Series Models

    cs.LG 2026-01 conditional novelty 6.0 of 10

    TimeSAE trains a sparse autoencoder with counterfactual and consistency losses to explain black-box time series predictions, claiming better faithfulness and out-of-distribution robustness than eight baselines.

  2. Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks

    cs.CV 2025-09 conditional novelty 6.0 of 10

    An unsupervised method, EDDP, jointly learns encoding-decoding direction pairs for concepts in CNN latent spaces, recovering interpretable and influential concepts without labels, validated on synthetic and real data.

  3. BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A self-supervision method makes multimodal LLMs align their input image embeddings with the model's own refined internal representations, improving visual QA scores over LLaVA baselines.

  4. Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?

    cs.AI 2025-06 conditional novelty 6.0 of 10

    Reasoning language models are systematically overconfident, deeper reasoning makes them more overconfident, and a two-stage introspective prompting method improves calibration for some models.

  5. REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control

    cs.CL 2025-11 unverdicted novelty 5.0 of 10

    REFLEX improves explainable fact-checking by using verdict-anchored style control and self-disagreement signals to disentangle fact from style in LLM outputs, achieving SOTA results with minimal self-refined samples.

Pith tools