Alternatives and similar repositories for Awesome-Sparse-Autoencoder

Users that are interested in Awesome-Sparse-Autoencoder are comparing it to the libraries listed below

• MikaStars39 / FeatureAlignment
  FeatureAlignment = Alignment + Mechanistic Interpretability
  ☆29Updated 5 months ago
• javiferran / sae_entities
  ☆60Updated 5 months ago
• Glaciohound / LM-Steer
  Official Code Repository for LM-Steer Paper: "Word Embeddings Are Steers for Language Models" (ACL 2024 Outstanding Paper Award)
  ☆123Updated last month
• yuzhaouoe / SAE-based-representation-engineering
  [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
  ☆63Updated 9 months ago
• hkust-nlp / Activation_Decoding
  In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)
  ☆60Updated last year
• OpenMOSS / Language-Model-SAEs
  For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.
  ☆145Updated last week
• ericwtodd / function_vectors
  Function Vectors in Large Language Models (ICLR 2024)
  ☆177Updated 4 months ago
• fc2869 / lo-fit
  LoFiT: Localized Fine-tuning on LLM Representations
  ☆40Updated 7 months ago
• roeehendel / icl_task_vectors
  ☆96Updated last year
• zepingyu0512 / neuron-attribution
  code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models
  ☆41Updated 9 months ago
• alisawuffles / proxy-tuning
  Code associated with Tuning Language Models by Proxy (Liu et al., 2024)
  ☆114Updated last year
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆124Updated 2 months ago
• epfl-dlab / llm-latent-language
  Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".
  ☆78Updated last year
• princeton-nlp / Edge-Pruning
  [NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".
  ☆59Updated last week
• qiuzh20 / EMoE
  Official PyTorch Implementation of EMoE: Unlocking Emergent Modularity in Large Language Models [main conference @ NAACL2024]
  ☆33Updated last year
• peterljq / Parsimonious-Concept-Engineering
  PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)
  ☆39Updated 9 months ago
• IBM / activation-steering
  [ICLR 2025] General-purpose activation steering library
  ☆94Updated last month
• saprmarks / geometry-of-truth
  ☆90Updated last year
• zjunlp / KnowledgeCircuits
  [NeurIPS 2024] Knowledge Circuits in Pretrained Transformers
  ☆153Updated 6 months ago
• RZFan525 / Awesome-ScalingLaws
  A curated list of awesome resources dedicated to Scaling Laws for LLMs
  ☆77Updated 2 years ago
• edenbiran / HoppingTooLate
  Exploring the Limitations of Large Language Models on Multi-Hop Queries
  ☆27Updated 5 months ago
• dannyallover / overthinking_the_truth
  ☆29Updated last year
• yihuaihong / ConceptVectors
  [EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"
  ☆36Updated last week
• cooperleong00 / Awesome-LLM-Interpretability
  A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..
  ☆265Updated 5 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆76Updated 5 months ago
• hkust-nlp / PEM_composition
  [NeurIPS 2023] Github repository for "Composing Parameter-Efficient Modules with Arithmetic Operations"
  ☆61Updated last year
• LiuAmber / RAHF
  [ACL 2024 main] Aligning Large Language Models with Human Preferences through Representation Engineering (https://aclanthology.org/2024.…
  ☆26Updated 11 months ago
• yaojin17 / Unlearning_LLM
  [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"
  ☆59Updated 10 months ago
• edenbiran / RippleEdits
  Evaluating the Ripple Effects of Knowledge Editing in Language Models
  ☆56Updated last year
• Thartvigsen / GRACE
  [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
  ☆79Updated 8 months ago