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 7.1k 1k

  2. lm-evaluation-harness Public

    A framework for few-shot evaluation of language models.

    Python 7.6k 2k

  3. minetest Public

    Forked from luanti-org/luanti

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

    C++ 64 10

  4. pythia Public

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

    Jupyter Notebook 2.3k 175

Repositories

Showing 10 of 156 repositories
  • polyapprox Public

    Closed-form polynomial approximations to neural networks

    Python 2 MIT 0 0 0 Updated Jan 25, 2025
  • lm-evaluation-harness Public

    A framework for few-shot evaluation of language models.

    Python 7,556 MIT 2,028 347 (21 issues need help) 101 Updated Jan 24, 2025
  • mdl Public

    Minimum Description Length probing for neural network representations

    Python 18 MIT 2 0 2 Updated Jan 24, 2025
  • Jupyter Notebook 138 Apache-2.0 16 7 (2 issues need help) 1 Updated Jan 24, 2025
  • basin-volume Public

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

    Jupyter Notebook 1 Apache-2.0 0 0 0 Updated Jan 24, 2025
  • clearnets Public
    Python 2 MIT 0 0 0 Updated Jan 24, 2025
  • transformer-reasoning Public Forked from OSU-NLP-Group/GrokkedTransformer

    Experiments in transformer knowledge and reasoning

    Jupyter Notebook 8 MIT 12 0 0 Updated Jan 23, 2025
  • cookbook Public

    Deep learning for dummies. All the practical details and useful utilities that go into working with real models.

    Python 756 Apache-2.0 38 8 1 Updated Jan 23, 2025
  • concept-erasure Public

    Erasing concepts from neural representations with provable guarantees

    Python 221 MIT 15 2 2 Updated Jan 22, 2025
  • gpt-neox Public

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

    Python 7,053 Apache-2.0 1,036 62 (3 issues need help) 23 Updated Jan 22, 2025