Learning to Read Out: Unembedding Dynamics in Language Model Pretraining
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 through the unembedding matrix, or readout, which is itself still being learned during pretraining. We show that a model's hidden states can en...
Matteo He, William F. Shen, Alexandru Iacob et al.
· 0 citations