Search Results for author:
Found 2 papers, 1 papers with code
Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT
Sparse dictionary learning has been a rapidly growing technique in mechanistic interpretability to attack superposition and extract more human-understandable features from model activations.
CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors
A common practice is to recast the task into a text-to-text format such that generative LLMs of natural language (NL-LLMs) like GPT-3 can be prompted to solve it.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
