Search Results for author: Igor Ostrovsky

Found 1 papers, 1 papers with code

Eliciting Latent Predictions from Transformers with the Tuned Lens

2 code implementations14 Mar 2023 Nora Belrose, Zach Furman, Logan Smith, Danny Halawi, Igor Ostrovsky, Lev McKinney, Stella Biderman, Jacob Steinhardt

We analyze transformers from the perspective of iterative inference, seeking to understand how model predictions are refined layer by layer.

Language Modelling

Cannot find the paper you are looking for? You can Submit a new open access paper.