Alternatives and similar repositories for steering-bench

Users that are interested in steering-bench are comparing it to the libraries listed below

• jiah-li / magic
  The repo for paper: Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models.
  ☆10Updated 8 months ago
• dynamical-inference / patchsae
  Implementation of PatchSAE as presented in "Sparse autoencoders reveal selective remapping of visual concepts during adaptation"
  ☆20Updated 3 months ago
• apple / ml-dataset-decomposition
  Official repo of dataset-decomposition paper [NeurIPS 2024]
  ☆19Updated 7 months ago
• aadityasingh / HARP
  ☆21Updated 7 months ago
• shauli-ravfogel / adv-kernel-removal
  ☆12Updated 2 years ago
• schwartz-lab-NLP / Tokens2Words
  ☆13Updated 5 months ago
• matchten / LoRA-Models-for-SAEs
  Code for reproducing our paper "Low Rank Adapting Models for Sparse Autoencoder Features"
  ☆14Updated 5 months ago
• clarifying-EM / model-organisms-for-EM
  Code repo for the model organisms and convergent directions of EM papers.
  ☆26Updated last month
• IBM / sae-steering
  Code to enable layer-level steering in LLMs using sparse auto encoders
  ☆25Updated 3 months ago
• facebookresearch / AbstentionBench
  A holistic benchmark for LLM abstention
  ☆48Updated last week
• Jiaxin-Wen / MisleadLM
  Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""
  ☆17Updated 10 months ago
• lingo-mit / lm-truthfulness
  ☆17Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆54Updated 4 months ago
• jiahai-feng / binding-iclr
  ☆15Updated last year
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆77Updated 9 months ago
• aypan17 / latentqa
  ☆21Updated 5 months ago
• peterljq / Parsimonious-Concept-Engineering
  PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)
  ☆39Updated 10 months ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆125Updated 2 months ago
• revelio-diffusion / revelio
  ☆25Updated 2 months ago
• scalable-model-editing / unified-model-editing
  We introduce EMMET and unify model editing with popular algorithms ROME and MEMIT.
  ☆24Updated 8 months ago
• arnab-api / romba
  Applies ROME and MEMIT on Mamba-S4 models
  ☆14Updated last year
• formll / resolving-scaling-law-discrepancies
  ☆20Updated last year
• zzwjames / FailureLLMUnlearning
  An official implementation of "Catastrophic Failure of LLM Unlearning via Quantization" (ICLR 2025)
  ☆29Updated 6 months ago
• sfeucht / footprints
  https://footprints.baulab.info
  ☆17Updated 11 months ago
• LRudL / sad
  Situational Awareness Dataset
  ☆37Updated 8 months ago
• dmis-lab / Monet
  [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers
  ☆70Updated 2 months ago
• NimrodShabtay / LiveXiv
  ☆11Updated last month
• koayon / atp_star
  PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
  ☆19Updated 7 months ago
• noanabeshima / tinymodel
  A TinyStories LM with SAEs and transcoders
  ☆13Updated 5 months ago
• tdooms / bilinear-decomposition
  Official repo for the paper "Weight-based Decomposition: A Case for Bilinear MLPs"
  ☆22Updated last month