Skip to content

Author

Raphael Sarfati

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Causal and Interpretable Structures in LLM Compositional Tasks

This work studies activations from ensembles of prompts that require inferring relationships between three tokens corresponding to a cyclic concept to correctly predict the next token and finds a consistent layerwise progression in how the joint dependence among the tokens is geometrically organized and causally used.

Gurbir Arora, To-Ni J. B. Liu, Jiajun Bao et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.