Alternatives and similar repositories for alignment_faking_public:

Users that are interested in alignment_faking_public are comparing it to the libraries listed below

• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆53Updated this week
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆41Updated 3 months ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆62Updated last year
• jacobdunefsky / transcoder_circuits
  ☆55Updated 3 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆62Updated 3 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆123Updated 8 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆29Updated 8 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆205Updated 4 months ago
• saprmarks / feature-circuits
  ☆143Updated 3 weeks ago
• EleutherAI / elk-generalization
  Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…
  ☆26Updated 8 months ago
• ejones313 / auditing-llms
  ☆52Updated last year
• EleutherAI / delphi
  ☆151Updated this week
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆116Updated last year
• saprmarks / geometry-of-truth
  ☆76Updated 6 months ago
• KihoPark / linear_rep_geometry
  ☆86Updated last week
• wesg52 / sparse-probing-paper
  Sparse probing paper full code.
  ☆53Updated last year
• amack315 / unsupervised-steering-vectors
  ☆29Updated 9 months ago
• hannamw / EAP-IG
  ☆18Updated 2 months ago
• adamkarvonen / SAEBench
  ☆52Updated this week
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆88Updated this week
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆38Updated 4 months ago
• koayon / atp_star
  PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
  ☆18Updated last month
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆14Updated 2 years ago
• redwoodresearch / Easy-Transformer
  ☆109Updated 6 months ago
• milesaturpin / cot-unfaithfulness
  ☆36Updated last year
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆88Updated last year
• locuslab / acr-memorization
  ☆30Updated 2 months ago
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆100Updated 10 months ago
• EleutherAI / w2s
  ☆21Updated 4 months ago
• pomonam / kronfluence
  Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature
  ☆133Updated 6 months ago