We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
Python 7.1k 1k
A framework for few-shot evaluation of language models.
Python 8k 2.2k
Forked from luanti-org/luanti
Minetest is an open source voxel game engine with easy modding and game creation
C++ 64 10
The hub for EleutherAI's work on interpretability and learning dynamics
Jupyter Notebook 2.4k 179
Precisely estimating the volume of basins in neural net parameter space corresponding to interpretable behaviors
Sparsify transformers with SAEs and transcoders
A library for mechanistic anomaly detection
Keeping language models honest by directly eliciting knowledge encoded in their activations.
Deep learning for dummies. All the practical details and useful utilities that go into working with real models.
Closed-form polynomial approximations to neural networks
