Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens
Sarse Readout Prism (SRP), which decomposes the readout using only its weights and expresses any token logit or logit difference as a sum of contributions from sparse readout features, reveals readout features as a new unit of analysis for lens readings, exposing structure that token identities can obscure and enabling...
Matteo He, William F. Shen, Xinchi Qiu et al.
· 0 citations