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 7k 1k

  2. lm-evaluation-harness Public

    A framework for few-shot evaluation of language models.

    Python 7.5k 2k

  3. minetest Public

    Forked from minetest/minetest

    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
  • lm-evaluation-harness Public

    A framework for few-shot evaluation of language models.

    Python 7,508 MIT 2,021 345 (21 issues need help) 104 Updated Jan 20, 2025
  • elk Public

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

    Python 192 MIT 33 15 (1 issue needs help) 10 Updated Jan 20, 2025
  • sae_overlap Public

    Acompanying code for our research on SAE feature overlap when trained on different seeds.

    Jupyter Notebook 1 Apache-2.0 0 0 0 Updated Jan 20, 2025
  • mdl Public

    Minimum Description Length probing for neural network representations

    Python 18 MIT 2 0 2 Updated Jan 20, 2025
  • clearnets Public
    Python 2 MIT 0 0 0 Updated Jan 19, 2025
  • Jupyter Notebook 137 Apache-2.0 16 8 (2 issues need help) 2 Updated Jan 18, 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 17, 2025
  • cookbook Public

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

    Python 754 Apache-2.0 38 8 0 Updated Jan 15, 2025
  • gpt-neox Public

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

    Python 7,046 Apache-2.0 1,035 62 (3 issues need help) 23 Updated Jan 16, 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 15, 2025