Skip to content

Pinned Loading

  1. gpt-neox Public

    An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

    Python 7.2k 1k

  2. lm-evaluation-harness Public

    A framework for few-shot evaluation of language models.

    Python 8.6k 2.3k

  3. minetest Public

    Forked from luanti-org/luanti

    Minetest is an open source voxel game engine with easy modding and game creation

    C++ 65 11

  4. pythia Public

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

    Jupyter Notebook 2.5k 182

Repositories

Showing 10 of 162 repositories
  • sparsify Public

    Sparsify transformers with SAEs and transcoders

    Python 514 MIT 70 3 (1 issue needs help) 0 Updated Apr 16, 2025
  • open-r1 Public Forked from huggingface/open-r1

    Fully open reproduction of DeepSeek-R1

    Python 1 Apache-2.0 2,192 0 0 Updated Apr 16, 2025
  • rllm Public Forked from agentica-project/rllm

    Democratizing Reinforcement Learning for LLMs

    Jupyter Notebook 0 MIT 270 0 0 Updated Apr 16, 2025
  • Megatron-LM Public Forked from NVIDIA/Megatron-LM

    Ongoing research training transformer models at scale

    Python 0 2,775 0 0 Updated Apr 15, 2025
  • lm-evaluation-harness Public

    A framework for few-shot evaluation of language models.

    Python 8,640 MIT 2,306 379 (19 issues need help) 115 Updated Apr 15, 2025
  • gpt-neox Public

    An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

    Python 7,156 Apache-2.0 1,048 64 (3 issues need help) 26 Updated Apr 14, 2025
  • elk Public

    Keeping language models honest by directly eliciting knowledge encoded in their activations.

    Python 199 MIT 33 15 (1 issue needs help) 10 Updated Apr 14, 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 167 Apache-2.0 25 4 5 Updated Apr 14, 2025
  • POSER Public Forked from sevdeawesome/POSER

    Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals

    Python 1 1 0 0 Updated Apr 13, 2025
  • tyche Public

    Precisely estimating the volume of basins in neural net parameter space corresponding to interpretable behaviors

    Jupyter Notebook 6 Apache-2.0 0 0 0 Updated Apr 9, 2025