Skip to content

@EleutherAI EleutherAI

Change the repository type filter

All

    Repositories list

    172 repositories

    • attribute

      Public
      Python
      •4•7•0•0•Updated Jul 5, 2025Jul 5, 2025

    • clt-training

      Public
      Sparsify transformers with cross-layer transcoders
      Python
      •
      MIT License
      •79•2•0•1•Updated Jul 4, 2025Jul 4, 2025

    • lm-evaluation-harness

      Public
      A framework for few-shot evaluation of language models.
      transformerlanguage-modelevaluation-framework
      Python
      •
      MIT License
      •2.5k•9.5k•423•138•Updated Jul 4, 2025Jul 4, 2025

    • bergson

      Public
      Mapping out the "memory" of neural nets with data attribution
      Python
      •
      MIT License
      •4•14•0•2•Updated Jul 3, 2025Jul 3, 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
      •32•188•5•1•Updated Jul 2, 2025Jul 2, 2025

    • sparsify

      Public
      Sparsify transformers with SAEs and transcoders
      Python
      •
      MIT License
      •79•581•4•0•Updated Jul 2, 2025Jul 2, 2025

    • aria

      Public
      Python
      •
      Apache License 2.0
      •11•56•0•0•Updated Jul 1, 2025Jul 1, 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•7.2k•61•24•Updated Jul 1, 2025Jul 1, 2025

    • elk

      Public
      Keeping language models honest by directly eliciting knowledge encoded in their activations.
      Python
      •
      MIT License
      •33•207•15•10•Updated Jun 30, 2025Jun 30, 2025

    • website

      Public
      New website for EleutherAI based on Hugo static site generator
      HTML
      •6•5•1•2•Updated Jun 29, 2025Jun 29, 2025

    • nanoGPT-mup

      Public
      The simplest, fastest repository for training/finetuning medium-sized GPTs.
      Python
      •
      MIT License
      •7.1k•141•0•0•Updated Jun 27, 2025Jun 27, 2025

    • djinn-problems

      Public
      Problems generated by djinn (exploitably verifiable coding problems)
      0•0•0•0•Updated Jun 27, 2025Jun 27, 2025

    • djinn

      Public
      Provide a lightweight framework for authoring and validating exploitable verifiable coding problems
      Python
      •0•0•0•0•Updated Jun 25, 2025Jun 25, 2025

    • attention-probes

      Public
      Linear probes with attention weighting
      Python
      •1•1•0•0•Updated Jun 24, 2025Jun 24, 2025

    • emergent-misalignment

      Public
      Python
      •
      MIT License
      •57•0•0•0•Updated Jun 13, 2025Jun 13, 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•801•8•1•Updated Jun 9, 2025Jun 9, 2025

    • pythia

      Public
      The hub for EleutherAI's work on interpretability and learning dynamics
      Jupyter Notebook
      •
      Apache License 2.0
      •188•2.6k•13•3•Updated Jun 9, 2025Jun 9, 2025

    • aria-utils

      Public
      MIDI tokenizers and pre-processing utils.
      Python
      •
      Apache License 2.0
      •1•1•0•0•Updated Jun 5, 2025Jun 5, 2025

    • truffaldino

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

    • DeeperSpeed

      Public
      DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.
      Python
      •
      Apache License 2.0
      •4.5k•168•0•1•Updated May 30, 2025May 30, 2025

    • open-r1

      Public
      Fully open reproduction of DeepSeek-R1
      Python
      •
      Apache License 2.0
      •2.3k•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

    • tyche

      Public
      Precisely estimating the volume of basins in neural net parameter space corresponding to interpretable behaviors
      Jupyter Notebook
      •
      Apache License 2.0
      •0•8•0•2•Updated May 21, 2025May 21, 2025

    • rtopk

      Public
      https://github.com/xiexi51/RTopK PyTorch wrapper
      Cuda
      •
      MIT License
      •0•1•0•0•Updated May 20, 2025May 20, 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
      •34•0•0•0•Updated May 15, 2025May 15, 2025

    • aria-amt

      Public
      Efficient and robust implementation of seq-to-seq automatic piano transcription.
      Python
      •
      Apache License 2.0
      •9•47•0•0•Updated May 5, 2025May 5, 2025

    • fmri

      Public
      Analogue of fMRI on artificial neural networks
      MIT License
      •0•2•0•0•Updated Apr 24, 2025Apr 24, 2025

    • rllm

      Public
      Democratizing Reinforcement Learning for LLMs
      Jupyter Notebook
      •
      MIT License
      •333•0•0•0•Updated Apr 16, 2025Apr 16, 2025

    • Megatron-LM

      Public
      Ongoing research training transformer models at scale
      Python
      •
      Other
      •2.9k•0•0•0•Updated Apr 15, 2025Apr 15, 2025

    • ccs

      Public
      Python
      •
      MIT License
      •6•7•1•4•Updated Mar 21, 2025Mar 21, 2025