repeng

Repository facts

Stars

762

Forks

67

Open issues and pull requests

20

Primary language

Jupyter Notebook

License

MIT License (MIT)

Owner

vgel · Personal account

Created

Jan 21, 2024

Last push

Sep 24, 2025

Topics

• language-model
• machine-learning
• representation-engineering
• sae
• saes
• sparse-autoencoder
• sparse-autoencoders
• transformers

Rank #7,313 of 9,507 in AI on GitHub, by stars. Data from the GitHub API, fetched Oct 18, 2026; star counts change daily. Stars measure popularity, not quality or safety, and a listing is not an endorsement. How this list is made

Related projects

Projects that share this one’s GitHub topics.

• 443

  Rank 443: arc53/DocsGPT

  Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.

  18,322 starsPythonMITLast push Oct 18, 2026

• 551

  Rank 551: BlinkDL/RWKV-LM

  RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combin…

  14,748 starsPythonApache-2.0Last push Sep 28, 2026

• 618

  Rank 618: neuml/txtai

  💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

  13,024 starsPythonApache-2.0Last push Oct 16, 2026

• 681

  Rank 681: speechbrain/speechbrain

  A PyTorch-based Speech Toolkit

  11,887 starsPythonApache-2.0Last push Oct 14, 2026

• 716

  Rank 716: huggingface/tokenizers

  💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

  11,183 starsRustApache-2.0Last push Oct 18, 2026

• 1,091

  Rank 1,091: EleutherAI/gpt-neox

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

  7,470 starsPythonApache-2.0Last push Oct 11, 2026