Skip to content
Change the repository type filter

All

    Repositories list

    • A framework for few-shot evaluation of language models.
      Python
      MIT License
      2.4k8.9k395120Updated May 6, 2025May 6, 2025
    • pythia

      Public
      The hub for EleutherAI's work on interpretability and learning dynamics
      Jupyter Notebook
      Apache License 2.0
      1842.5k263Updated May 6, 2025May 6, 2025
    • website

      Public
      New website for EleutherAI based on Hugo static site generator
      HTML
      5403Updated May 5, 2025May 5, 2025
    • elk

      Public
      Keeping language models honest by directly eliciting knowledge encoded in their activations.
      Python
      MIT License
      332011510Updated May 5, 2025May 5, 2025
    • sparsify

      Public
      Sparsify transformers with SAEs and transcoders
      Python
      MIT License
      7152401Updated May 5, 2025May 5, 2025
    • delphi

      Public
      Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models know themselves through automated interpretability.
      Python
      Apache License 2.0
      2517042Updated May 5, 2025May 5, 2025
    • aria-amt

      Public
      Efficient and robust implementation of seq-to-seq automatic piano transcription.
      Python
      Apache License 2.0
      94100Updated May 5, 2025May 5, 2025
    • wmdp

      Public
      WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning method which reduces LLM performance on WMDP while retaining general capabilities.
      Jupyter Notebook
      MIT License
      32000Updated May 5, 2025May 5, 2025
    • gpt-neox

      Public
      An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
      Python
      Apache License 2.0
      1.1k7.2k6427Updated May 3, 2025May 3, 2025
    • The simplest, fastest repository for training/finetuning medium-sized GPTs.
      Python
      MIT License
      6.8k10700Updated May 2, 2025May 2, 2025
    • Investigating goal instability in RL
      Python
      MIT License
      0000Updated May 2, 2025May 2, 2025
    • attribute

      Public
      JavaScript
      1000Updated May 1, 2025May 1, 2025
    • cookbook

      Public
      Deep learning for dummies. All the practical details and useful utilities that go into working with real models.
      Python
      Apache License 2.0
      4078980Updated Apr 30, 2025Apr 30, 2025
    • tyche

      Public
      Precisely estimating the volume of basins in neural net parameter space corresponding to interpretable behaviors
      Jupyter Notebook
      Apache License 2.0
      0801Updated Apr 30, 2025Apr 30, 2025
    • open-r1

      Public
      Fully open reproduction of DeepSeek-R1
      Python
      Apache License 2.0
      2.2k200Updated Apr 30, 2025Apr 30, 2025
    • fmri

      Public
      Analogue of fMRI on artificial neural networks
      MIT License
      0200Updated Apr 24, 2025Apr 24, 2025
    • POSER

      Public
      Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals
      Python
      1100Updated Apr 24, 2025Apr 24, 2025
    • rllm

      Public
      Democratizing Reinforcement Learning for LLMs
      Jupyter Notebook
      MIT License
      295000Updated Apr 16, 2025Apr 16, 2025
    • Ongoing research training transformer models at scale
      Python
      Other
      2.7k000Updated Apr 15, 2025Apr 15, 2025
    • rtopk

      Public
      Cuda
      MIT License
      0100Updated Apr 5, 2025Apr 5, 2025
    • DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.
      Python
      Apache License 2.0
      4.4k16701Updated Apr 1, 2025Apr 1, 2025
    • ccs

      Public
      Python
      MIT License
      6614Updated Mar 21, 2025Mar 21, 2025
    • MIT License
      0000Updated Mar 17, 2025Mar 17, 2025
    • cupbearer

      Public
      A library for mechanistic anomaly detection
      Jupyter Notebook
      MIT License
      10600Updated Feb 26, 2025Feb 26, 2025
    • clearnets

      Public
      Python
      MIT License
      0400Updated Feb 18, 2025Feb 18, 2025
    • Closed-form polynomial approximations to neural networks
      Python
      MIT License
      11301Updated Jan 31, 2025Jan 31, 2025
    • Experiments in transformer knowledge and reasoning
      Jupyter Notebook
      MIT License
      201000Updated Jan 30, 2025Jan 30, 2025
    • A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.
      Python
      Apache License 2.0
      416000Updated Jan 29, 2025Jan 29, 2025
    • Acompanying code for our research on SAE feature overlap when trained on different seeds.
      Jupyter Notebook
      Apache License 2.0
      1300Updated Jan 28, 2025Jan 28, 2025
    • mdl

      Public
      Minimum Description Length probing for neural network representations
      Python
      MIT License
      21902Updated Jan 28, 2025Jan 28, 2025