Alternatives and similar repositories for alignment_faking_public

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

• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆55Updated 7 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆226Updated 8 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆108Updated 4 months ago
• jacobdunefsky / transcoder_circuits
  ☆131Updated 7 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆67Updated 2 months ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆20Updated 7 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆158Updated last year
• amack315 / unsupervised-steering-vectors
  ☆31Updated last year
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆94Updated last year
• redwoodresearch / Easy-Transformer
  ☆120Updated 10 months ago
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆109Updated last year
• saprmarks / feature-circuits
  ☆173Updated 2 months ago
• milesaturpin / cot-unfaithfulness
  ☆44Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆52Updated last month
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆185Updated this week
• saprmarks / geometry-of-truth
  ☆85Updated 10 months ago
• IBM / activation-steering
  General-purpose activation steering library
  ☆78Updated last month
• 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…
  ☆27Updated last year
• adamkarvonen / SAEBench
  ☆101Updated 3 weeks ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆72Updated 3 months ago
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆15Updated 3 years ago
• neelnanda-io / Crosscoders
  ☆44Updated 7 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆121Updated last year
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆65Updated last year
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆35Updated last year
• Nix07 / finetuning
  This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…
  ☆27Updated last year
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆233Updated last week
• KihoPark / linear_rep_geometry
  ☆95Updated 4 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆214Updated 9 months ago
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆255Updated last year