Search Results for author:
Found 4 papers, 2 papers with code
Grokking Group Multiplication with Cosets
We use the group Fourier transform over the symmetric group $S_n$ to reverse engineer a 1-layer feedforward network that has "grokked" the multiplication of $S_5$ and $S_6$.
Characterizing Mechanisms for Factual Recall in Language Models
By scaling up or down the value vector of these heads, we can control the likelihood of using the in-context answer on new data.
Are Language Models Worse than Humans at Following Prompts? It's Complicated
However, recent work finds that models can perform surprisingly well when given intentionally irrelevant or misleading prompts.
Does CLIP Bind Concepts? Probing Compositionality in Large Image Models
In this work, we focus on the ability of a large pretrained vision and language model (CLIP) to encode compositional concepts and to bind variables in a structure-sensitive way (e. g., differentiating ''cube behind sphere'' from ''sphere behind cube'').
