2 citations · 6 across the 18 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.CL2023
Outlier Dimensions Encode Task-Specific Knowledge
William Rudman, Catherine Chen, Carsten Eickhoff
Representations from large language models (LLMs) are known to be dominated by a small subset of dimensions with exceedingly high variance. Previous works have argued that although…
cs.CL2023★ 2 cited
Stable Anisotropic Regularization
William Rudman, Carsten Eickhoff
Given the success of Large Language Models (LLMs), there has been considerable interest in studying the properties of model activations. The literature overwhelmingly agrees that L…