Search Results for author:
Found 5 papers, 4 papers with code
Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
We introduce methods for discovering and applying sparse feature circuits.
Structured World Representations in Maze-Solving Transformers
Transformer models underpin many recent advances in practical machine learning applications, yet understanding their internal behavior continues to elude researchers.
Attribution Patching Outperforms Automated Circuit Discovery
Automated interpretability research has recently attracted attention as a potential research direction that could scale explanations of neural network behavior to large models.
An Adversarial Example for Direct Logit Attribution: Memory Management in gelu-4l
That is, clearing residual stream directions set by earlier layers by reading in information and writing out the negative version.
A Configurable Library for Generating and Manipulating Maze Datasets
Understanding how machine learning models respond to distributional shifts is a key research challenge.
