Skip to content

@EleutherAI EleutherAI

Change the repository type filter

All

    Repositories list

    178 repositories

    • bergson

      Public
      Mapping out the "memory" of neural nets with data attribution
      interpretabilitymechanistic-interpretabilitydata-attribution
      Python
      •
      MIT License
      •10•32•4•7•Updated Nov 12, 2025Nov 12, 2025

    • lm-evaluation-harness

      Public
      A framework for few-shot evaluation of language models.
      transformerlanguage-modelevaluation-framework
      Python
      •
      MIT License
      •2.8k•11k•510•164•Updated Nov 11, 2025Nov 11, 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
      •51•223•3•3•Updated Nov 10, 2025Nov 10, 2025

    • elk

      Public
      Keeping language models honest by directly eliciting knowledge encoded in their activations.
      Python
      •
      MIT License
      •32•212•15•10•Updated Nov 10, 2025Nov 10, 2025

    • sparsify

      Public
      Sparsify transformers with SAEs and transcoders
      Python
      •
      MIT License
      •86•653•5•2•Updated Nov 10, 2025Nov 10, 2025

    • tuned-lens

      Public
      Tools for understanding how transformer predictions are built layer-by-layer
      Python
      •
      MIT License
      •59•2•0•0•Updated Nov 10, 2025Nov 10, 2025

    • deep-ignorance

      Public
      Python
      •2•10•2•0•Updated Nov 6, 2025Nov 6, 2025

    • vllm

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      •
      Apache License 2.0
      •11k•0•0•0•Updated Nov 3, 2025Nov 3, 2025

    • gamescope

      Public
      Can interpretability methods confer an advantage in competitive games?
      Python
      •
      Apache License 2.0
      •0•2•0•0•Updated Oct 31, 2025Oct 31, 2025

    • djinn

      Public
      Generating, validating and running exploitable verifiable coding problems
      Python
      •0•7•0•0•Updated Oct 31, 2025Oct 31, 2025

    • djinn-problems

      Public
      Problems generated by djinn (exploitably verifiable coding problems)
      0•0•0•0•Updated Oct 31, 2025Oct 31, 2025

    • hackable-bergson

      Public
      Simplified library for mapping out the "memory" of neural nets with data attribution
      Python
      •
      MIT License
      •10•0•0•0•Updated Oct 26, 2025Oct 26, 2025

    • website

      Public
      New website for EleutherAI based on Hugo static site generator
      HTML
      •7•6•1•2•Updated Oct 14, 2025Oct 14, 2025

    • emergent-misalignment

      Public
      Jupyter Notebook
      •
      MIT License
      •71•1•0•0•Updated Oct 9, 2025Oct 9, 2025

    • aria

      Public
      Official repository for the paper: Scaling Self-Supervised Representation Learning for Symbolic Piano Performance (ISMIR 2025)
      Python
      •
      Apache License 2.0
      •13•82•0•0•Updated Oct 8, 2025Oct 8, 2025

    • gpt-neox

      Public
      An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
      transformerslanguage-modelgpt-3deepspeed-library
      Python
      •
      Apache License 2.0
      •1.1k•7.3k•61•26•Updated Sep 26, 2025Sep 26, 2025

    • DeeperSpeed

      Public
      DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.
      Python
      •
      Apache License 2.0
      •4.6k•170•0•1•Updated Sep 26, 2025Sep 26, 2025

    • clt-training

      Public
      Sparsify transformers with cross-layer transcoders
      Python
      •
      MIT License
      •86•16•0•2•Updated Aug 12, 2025Aug 12, 2025

    • attribute

      Public
      Python
      •6•12•0•1•Updated Aug 6, 2025Aug 6, 2025

    • attention-probes

      Public
      Linear probes with attention weighting
      Python
      •1•7•0•0•Updated Aug 2, 2025Aug 2, 2025

    • verifiers

      Public
      Verifiers for LLM Reinforcement Learning
      Python
      •
      MIT License
      •430•0•0•0•Updated Jul 31, 2025Jul 31, 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
      •42•822•8•3•Updated Jul 29, 2025Jul 29, 2025

    • SkipTranscoderSAEBench

      Public
      Python
      •0•1•0•0•Updated Jul 22, 2025Jul 22, 2025

    • aria-utils

      Public
      MIDI tokenizers and pre-processing utils.
      Python
      •
      Apache License 2.0
      •3•5•3•1•Updated Jul 21, 2025Jul 21, 2025

    • aria-amt

      Public
      Efficient and robust implementation of seq-to-seq automatic piano transcription.
      Python
      •
      Apache License 2.0
      •9•60•0•0•Updated Jul 9, 2025Jul 9, 2025

    • nanoGPT-mup

      Public
      The simplest, fastest repository for training/finetuning medium-sized GPTs.
      Python
      •
      MIT License
      •8.3k•172•2•0•Updated Jun 27, 2025Jun 27, 2025

    • pythia

      Public
      The hub for EleutherAI's work on interpretability and learning dynamics
      Jupyter Notebook
      •
      Apache License 2.0
      •195•2.7k•15•3•Updated Jun 9, 2025Jun 9, 2025

    • truffaldino

      Public
      Investigating goal instability in RL
      Python
      •
      MIT License
      •0•1•0•0•Updated Jun 2, 2025Jun 2, 2025

    • open-r1

      Public
      Fully open reproduction of DeepSeek-R1
      Python
      •
      Apache License 2.0
      •2.4k•4•0•0•Updated May 21, 2025May 21, 2025

    • POSER

      Public
      Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals
      Python
      •4•2•0•0•Updated May 21, 2025May 21, 2025