42 citations · 157 across the 17 of their papers we have counts for
Showing 2023 · cs.LGShow all
2 papers · 2 filters
cs.LG2023★ 1 cited
Interpretability Illusions in the Generalization of Simplified Models
Dan Friedman, Andrew Lampinen, Lucas Dixon +2
A common method to study deep learning systems is to use simplified model representations--for example, using singular value decomposition to visualize the model's hidden states in…
cs.LG2023★ 13 cited
Learning Transformer Programs
Dan Friedman, Alexander Wettig, Danqi Chen
Recent research in mechanistic interpretability has attempted to reverse-engineer Transformer models by carefully inspecting network weights and activations. However, these approac…