Alternatives and similar repositories for train_sparse_autoencoder

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

• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆136Updated 3 months ago
• yihuaihong / ConceptVectors
  [EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"
  ☆35Updated last month
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆80Updated 7 months ago
• milesaturpin / cot-unfaithfulness
  ☆48Updated last year
• MaheepChaudhary / SAE-Ravel
  Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…
  ☆12Updated 8 months ago
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆56Updated last year
• IBM / activation-steering
  [ICLR 2025] General-purpose activation steering library
  ☆108Updated 2 weeks ago
• peterljq / Parsimonious-Concept-Engineering
  PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)
  ☆40Updated 11 months ago
• yaojin17 / Unlearning_LLM
  [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"
  ☆60Updated last year
• ykwon0407 / DataInf
  DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)
  ☆76Updated last year
• Thartvigsen / GRACE
  [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
  ☆81Updated 9 months ago
• javiferran / sae_entities
  ☆63Updated 7 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆41Updated last year
• fc2869 / lo-fit
  LoFiT: Localized Fine-tuning on LLM Representations
  ☆41Updated 8 months ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆24Updated 10 months ago
• logix-project / logix
  AI Logging for Interpretability and Explainability🔬
  ☆128Updated last year
• adamkarvonen / SAEBench
  ☆125Updated 2 weeks ago
• hannamw / EAP-IG
  ☆51Updated 2 months ago
• locuslab / acr-memorization
  ☆37Updated 9 months ago
• yuzhaouoe / SAE-based-representation-engineering
  [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
  ☆64Updated 10 months ago
• DanielSc4 / Dynamic-Activation-Composition
  Materials for "Multi-property Steering of Large Language Models with Dynamic Activation Composition"
  ☆12Updated 10 months ago
• balevinstein / Probes
  ☆56Updated 2 years ago
• paul-rottger / xstest
  Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆116Updated 7 months ago
• roeehendel / icl_task_vectors
  ☆97Updated last year
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆77Updated 2 months ago
• dannyallover / overthinking_the_truth
  ☆29Updated last year
• epfl-dlab / llm-latent-language
  Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".
  ☆80Updated last year
• tim-lawson / mlsae
  Multi-Layer Sparse Autoencoders (ICLR 2025)
  ☆25Updated 7 months ago
• yfqiu-nlp / sea-llm
  Code for the paper "Spectral Editing of Activations for Large Language Model Alignments"
  ☆26Updated 9 months ago
• saprmarks / geometry-of-truth
  ☆91Updated last year