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
  ☆161Updated 6 months ago
• milesaturpin / cot-unfaithfulness
  ☆51Updated 2 years ago
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆57Updated 2 months ago
• IBM / activation-steering
  [ICLR 2025] General-purpose activation steering library
  ☆132Updated 3 months ago
• 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 11 months ago
• yihuaihong / ConceptVectors
  [EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"
  ☆39Updated 4 months ago
• yuzhaouoe / SAE-based-representation-engineering
  [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
  ☆68Updated last year
• jacobdunefsky / llm-steering-opt
  Tools for optimizing steering vectors in LLMs.
  ☆15Updated 8 months ago
• balevinstein / Probes
  ☆57Updated 2 years ago
• ykwon0407 / DataInf
  DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)
  ☆79Updated last year
• deeplearning-wisc / haloscope
  source code for NeurIPS'24 paper "HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection"
  ☆64Updated 8 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆85Updated 9 months ago
• javiferran / sae_entities
  ☆68Updated 9 months ago
• peterljq / Parsimonious-Concept-Engineering
  PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)
  ☆41Updated last year
• Thartvigsen / GRACE
  [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
  ☆82Updated last year
• paul-rottger / xstest
  Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆118Updated 10 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆44Updated last year
• chrisliu298 / awesome-representation-engineering
  A resource repository for representation engineering in large language models
  ☆145Updated last year
• logix-project / logix
  AI Logging for Interpretability and Explainability🔬
  ☆136Updated last year
• bpwu1 / confidence-regulation-neurons
  Confidence Regulation Neurons in Language Models (NeurIPS 2024)
  ☆15Updated 11 months ago
• hannamw / EAP-IG
  ☆68Updated 5 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆100Updated 2 years ago
• locuslab / acr-memorization
  ☆37Updated last year
• saprmarks / geometry-of-truth
  ☆97Updated last year
• dannyallover / overthinking_the_truth
  ☆29Updated last year
• yfqiu-nlp / sea-llm
  Code for the paper "Spectral Editing of Activations for Large Language Model Alignments"
  ☆29Updated last year
• fc2869 / lo-fit
  LoFiT: Localized Fine-tuning on LLM Representations
  ☆44Updated 11 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆84Updated 5 months ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆66Updated 2 years ago
• ericwtodd / function_vectors
  Function Vectors in Large Language Models (ICLR 2024)
  ☆189Updated 8 months ago