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.
  ☆65Updated last month
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆50Updated last month
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆55Updated 7 months ago
• jacobdunefsky / transcoder_circuits
  ☆120Updated 6 months 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 last year
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆101Updated 3 months ago
• saprmarks / feature-circuits
  ☆170Updated last month
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆20Updated 6 months ago
• amack315 / unsupervised-steering-vectors
  ☆31Updated last year
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆34Updated last year
• ArthurConmy / Automatic-Circuit-Discovery
  ☆223Updated 8 months ago
• neelnanda-io / Crosscoders
  ☆43Updated 6 months ago
• callummcdougall / sae_visualizer
  ☆28Updated last year
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆15Updated 3 years ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆93Updated last year
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆121Updated last year
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆23Updated this week
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆180Updated this week
• KoyenaPal / future-lens
  Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
  ☆18Updated last year
• hannamw / EAP-IG
  ☆34Updated 2 weeks ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆154Updated last year
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆89Updated last week
• saprmarks / geometry-of-truth
  ☆83Updated 9 months ago
• UKGovernmentBEIS / control-arena
  ControlArena is a suite of realistic settings, mimicking complex deployment environments, for running control evaluations. This is an alp…
  ☆60Updated this week
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆140Updated last month
• KihoPark / linear_rep_geometry
  ☆93Updated 3 months ago
• Cadenza-Labs / sleeper-agents
  ☆10Updated 10 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆200Updated 5 months ago
• koayon / atp_star
  PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
  ☆18Updated 4 months ago
• milesaturpin / cot-unfaithfulness
  ☆44Updated last year