Pith. sign in

REVIEW 2 cited by

How to Dissect a Muppet: The Structure of Transformer Embedding Spaces

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 2206.03529 v1 pith:5OJRVABT submitted 2022-06-07 cs.CL

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

Pretrained embeddings based on the Transformer architecture have taken the NLP community by storm. We show that they can mathematically be reframed as a sum of vector factors and showcase how to use this reframing to study the impact of each component. We provide evidence that multi-head attentions and feed-forwards are not equally useful in all downstream applications, as well as a quantitative overview of the effects of finetuning on the overall embedding space. This approach allows us to draw connections to a wide range of previous studies, from vector space anisotropy to attention weights.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.

  2. The Algorithm Is Not the Behavior: Learned Priors Override Look-Ahead in a Chess-Playing Neural Network

    cs.LG 2025-08 reject novelty 5.0 of 10

    The paper demonstrates non-monotonic move-policy dynamics in a chess transformer, but its abstract claims a causal safety-prior override result that never appears in the body.

Pith tools