REVIEW 5 cited by
The Geometry of Tokens in Internal Representations of 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
read the original abstract
We investigate the relationship between the geometry of token embeddings and their role in the next token prediction within transformer models. An important aspect of this connection uses the notion of empirical measure, which encodes the distribution of token point clouds across transformer layers and drives the evolution of token representations in the mean-field interacting picture. We use metrics such as intrinsic dimension, neighborhood overlap, and cosine similarity to observationally probe these empirical measures across layers. To validate our approach, we compare these metrics to a dataset where the tokens are shuffled, which disrupts the syntactic and semantic structure. Our findings reveal a correlation between the geometric properties of token embeddings and the cross-entropy loss of next token predictions, implying that prompts with higher loss values have tokens represented in higher-dimensional spaces.
Forward citations
Cited by 5 Pith papers
-
Metaphor Tracer: A Theory-Informed Analysis of Hidden States
Hidden-state aggregator and differentiator scores, frozen on one text, track within-text organization across models and align with engineered registers and psychoanalytic marks while dissociating from information and ...
-
Attention's forward pass and Frank-Wolfe
Hardmax self-attention is shown to be a Frank-Wolfe iteration; with positive-definite key-query it converges to Voronoi-cell vertices, and a Markov-chain version of soft attention is metastable there for exponential-i...
-
Geometric Configurations of Perturbed Jailbreak Prompts
In six small open-weight LLMs, jailbreak prompts are linearly separable in last-token embeddings by surface form, but not by refusal/compliance behavior.
-
An Analysis of Residual-Stream Geometry Across Transformer Depth
Across six instruction-tuned transformers, residual-stream layer transitions follow a model-specific, condition-stable depth curve: large early and late updates, a quiet middle, near-flat rotation, and a rising final ...
-
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs
A submission whose abstract describes a new graph neural operator for PDEs but whose full text is a different paper, leaving the claimed method and results unverifiable.
Discussion (0). Sign in to comment.