Skip to content

Pinned Loading

  1. gpt-neox 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 lm-evaluation-harness Public

    A framework for few-shot evaluation of language models.

    Python 7.3k 2k

  3. minetest 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 pythia Public

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

    Jupyter Notebook 2.3k 175

Repositories

Showing 10 of 155 repositories
  • transformer-reasoning Public Forked from OSU-NLP-Group/GrokkedTransformer

    Experiments in transformer knowledge and reasoning

    EleutherAI/transformer-reasoning’s past year of commit activity
    Jupyter Notebook 5 MIT 12 0 0 Updated Dec 21, 2024
  • lm-evaluation-harness Public

    A framework for few-shot evaluation of language models.

    EleutherAI/lm-evaluation-harness’s past year of commit activity
    Python 7,270 MIT 1,964 339 (22 issues need help) 101 Updated Dec 20, 2024
  • mdl Public

    Minimum Description Length probing for neural network representations

    EleutherAI/mdl’s past year of commit activity
    Python 17 MIT 2 0 2 Updated Dec 20, 2024
  • gpt-neox Public

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

    EleutherAI/gpt-neox’s past year of commit activity
    Python 7,004 Apache-2.0 1,024 62 (3 issues need help) 22 Updated Dec 19, 2024
  • basin-volume Public

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

    EleutherAI/basin-volume’s past year of commit activity
    Jupyter Notebook 0 Apache-2.0 0 0 0 Updated Dec 19, 2024
  • sae Public

    Sparse autoencoders

    EleutherAI/sae’s past year of commit activity
    Python 385 MIT 51 5 2 Updated Dec 18, 2024
  • EleutherAI/sae-auto-interp’s past year of commit activity
    Jupyter Notebook 126 Apache-2.0 13 6 (2 issues need help) 1 Updated Dec 18, 2024
  • concept-erasure Public

    Erasing concepts from neural representations with provable guarantees

    EleutherAI/concept-erasure’s past year of commit activity
    Python 215 MIT 15 2 2 Updated Dec 18, 2024
  • aria Public
    EleutherAI/aria’s past year of commit activity
    Python 42 Apache-2.0 11 0 0 Updated Dec 17, 2024
  • elk Public

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

    EleutherAI/elk’s past year of commit activity
    Python 187 MIT 33 15 (1 issue needs help) 10 Updated Dec 16, 2024