Alternatives and similar repositories for steering-bench

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

• dynamical-inference / patchsae
  Implementation of PatchSAE as presented in "Sparse autoencoders reveal selective remapping of visual concepts during adaptation"
  ☆28Updated 3 months ago
• apple / ml-dataset-decomposition
  Official repo of dataset-decomposition paper [NeurIPS 2024]
  ☆20Updated last year
• aypan17 / latentqa
  ☆27Updated 2 months ago
• wesg52 / universal-neurons
  Universal Neurons in GPT2 Language Models
  ☆30Updated last year
• clarifying-EM / model-organisms-for-EM
  Code repo for the model organisms and convergent directions of EM papers.
  ☆45Updated 4 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆83Updated last year
• matchten / LoRA-Models-for-SAEs
  Code for reproducing our paper "Low Rank Adapting Models for Sparse Autoencoder Features"
  ☆17Updated 10 months ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆162Updated 7 months ago
• formll / resolving-scaling-law-discrepancies
  ☆20Updated 2 months ago
• Nix07 / finetuning
  This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…
  ☆30Updated 3 months ago
• bartbussmann / matryoshka_sae
  ☆57Updated last year
• koayon / atp_star
  PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
  ☆20Updated last year
• tdooms / bilinear-decomposition
  Official repo for the paper "Bilinear MLPs enable weight-based mechanistic interpretability".
  ☆28Updated 5 months ago
• peterljq / Parsimonious-Concept-Engineering
  PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)
  ☆42Updated last week
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆57Updated 3 months ago
• jkallini / mission-impossible-language-models
  Code repository for the paper "Mission: Impossible Language Models."
  ☆56Updated 4 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆56Updated 9 months ago
• zzwjames / FailureLLMUnlearning
  An official implementation of "Catastrophic Failure of LLM Unlearning via Quantization" (ICLR 2025)
  ☆36Updated 11 months ago
• ckkissane / sae-transfer
  Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"
  ☆13Updated last year
• IBM / sae-steering
  Code to enable layer-level steering in LLMs using sparse auto encoders
  ☆28Updated 4 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆86Updated last month
• KempnerInstitute / overcomplete
  👋 Overcomplete is a Vision-based SAE Toolbox
  ☆117Updated last month
• aadityasingh / HARP
  ☆23Updated last year
• efarrell1 / train_sparse_autoencoder
  Trains Sparse Autoencoders based on outputs from language models
  ☆11Updated last year
• jiahai-feng / binding-iclr
  ☆16Updated last year
• jiah-li / magic
  The repo for paper: Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models.
  ☆13Updated last year
• shauli-ravfogel / adv-kernel-removal
  ☆12Updated 3 years ago
• IBM / ColPret
  Efficient Scaling laws and collaborative pretraining.
  ☆20Updated 4 months ago
• aryamanarora / causalgym
  CausalGym: Benchmarking causal interpretability methods on linguistic tasks
  ☆51Updated last year
• multimodal-interpretability / maia
  Official implementation of MAIA, A Multimodal Automated Interpretability Agent
  ☆102Updated 3 months ago