Alternatives and similar repositories for alignment_faking_public

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

• ArthurConmy / Automatic-Circuit-Discovery
  ☆262Updated last year
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆203Updated last year
• jacobdunefsky / transcoder_circuits
  ☆193Updated last year
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆289Updated 2 years ago
• saprmarks / feature-circuits
  ☆197Updated 2 months ago
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆234Updated last week
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆84Updated 5 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆135Updated 10 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆285Updated last year
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆63Updated last year
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆233Updated last year
• redwoodresearch / Easy-Transformer
  ☆134Updated last year
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆132Updated 2 years ago
• IBM / activation-steering
  [ICLR 2025] General-purpose activation steering library
  ☆132Updated 3 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆100Updated 2 years ago
• neelnanda-io / Crosscoders
  ☆58Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆56Updated 8 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆303Updated last year
• adamkarvonen / SAEBench
  ☆138Updated this week
• saprmarks / geometry-of-truth
  ☆97Updated last year
• KihoPark / linear_rep_geometry
  ☆112Updated 10 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆85Updated 9 months ago
• curt-tigges / probity
  ☆19Updated 8 months ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆66Updated 2 years ago
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆324Updated 6 months ago
• amack315 / unsupervised-steering-vectors
  ☆36Updated last year
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆144Updated 2 weeks ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆44Updated last year
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆25Updated last year
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆123Updated last year