Alternatives and similar repositories for SAE-TS:

Users that are interested in SAE-TS are comparing it to the libraries listed below

• Cadenza-Labs / sleeper-agents
  ☆10Updated 8 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆43Updated 4 months ago
• neelnanda-io / Crosscoders
  ☆31Updated 3 months ago
• callummcdougall / sae_visualizer
  ☆26Updated 11 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆42Updated 4 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆56Updated 3 weeks ago
• mishajw / repeng
  Experiments with representation engineering
  ☆11Updated last year
• adamkarvonen / SAEBench
  ☆62Updated this week
• annahdo / implementing_activation_steering
  A collection of different ways to implement accessing and modifying internal model activations for LLMs
  ☆13Updated 4 months ago
• jacobdunefsky / transcoder_circuits
  ☆60Updated 3 months ago
• amack315 / unsupervised-steering-vectors
  ☆29Updated 10 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆90Updated 2 weeks ago
• EleutherAI / delphi
  ☆159Updated this week
• koayon / atp_star
  PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
  ☆18Updated last month
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆29Updated 9 months ago
• KoyenaPal / future-lens
  Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
  ☆18Updated last year
• tilde-research / sieve
  Applying SAEs for fine-grained control
  ☆14Updated 2 months ago
• saprmarks / feature-circuits
  ☆148Updated this week
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆63Updated last year
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆91Updated last year
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆14Updated 2 years ago
• saprmarks / geometry-of-truth
  ☆80Updated 7 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆120Updated last year
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆125Updated 9 months ago
• redwoodresearch / alignment_faking_public
  ☆41Updated last month
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆184Updated 2 months ago
• jbloomAus / SAEDashboard
  ☆32Updated 2 weeks ago
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆40Updated 5 months ago
• redwoodresearch / Easy-Transformer
  ☆112Updated 7 months ago