4 citations · 8 across the 16 of their papers we have counts for
Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Learning to Read Out: Unembedding Dynamics in Language Model Pretraining
Matteo He, William F. Shen, Alex Iacob +3
When does a language model acquire a capability? Developmental studies usually answer this by tracking when models start producing the correct token. But that prediction passes thr…
cs.CL2026
Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens
Matteo He, William F. Shen, Xinchi Qiu +1
A language model's prediction of its next token develops across layers, and lens methods track this process by decoding intermediate hidden states into tokens. But a lens reading r…