Google Research

The hub for EleutherAI's work on interpretability and learning dynamics

Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more

A multi-task learning example for the paper https://arxiv.org/abs/1705.07115

Python package for measuring memorization in LLMs.

Materials for EACL2024 tutorial: Transformer-specific Interpretability

Official Repository for Dataset Inference for LLMs

Open source readability metrics for Portuguese and English.