Search Results for author:
Found 3 papers, 3 papers with code
Algorithmic progress in language models
We investigate the rate at which algorithms for pre-training language models have improved since the advent of deep learning.
Opening the AI black box: program synthesis via mechanistic interpretability
We present MIPS, a novel method for program synthesis based on automated mechanistic interpretability of neural networks trained to perform the desired task, auto-distilling the learned algorithm into Python code.
Universal Neurons in GPT2 Language Models
In other words, are neural mechanisms universal across different models?
Cannot find the paper you are looking for? You can
Submit a new open access paper.
