Alternatives and similar repositories for SAE-Reasoning

Users that are interested in SAE-Reasoning are comparing it to the libraries listed below

• ericwtodd / function_vectors
  Function Vectors in Large Language Models (ICLR 2024)
  ☆167Updated last month
• javiferran / sae_entities
  ☆36Updated 2 months ago
• ahans30 / goldfish-loss
  [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs
  ☆87Updated 6 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆72Updated 2 months ago
• roeehendel / icl_task_vectors
  ☆94Updated last year
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆55Updated 7 months ago
• fc2869 / lo-fit
  LoFiT: Localized Fine-tuning on LLM Representations
  ☆39Updated 4 months ago
• OpenMOSS / Language-Model-SAEs
  For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.
  ☆116Updated this week
• dmis-lab / Monet
  [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers
  ☆68Updated 4 months ago
• epfl-dlab / llm-latent-language
  Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".
  ☆76Updated last year
• deeplearning-wisc / args
  ☆40Updated last year
• Nix07 / finetuning
  This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…
  ☆26Updated last year
• Leiay / looped_transformer
  ☆26Updated last year
• facebookresearch / iGSM
  The code for creating the iGSM datasets in papers "Physics of Language Models Part 2.1, Grade-School Math and the Hidden Reasoning Proces…
  ☆54Updated 4 months ago
• DAMO-NLP-SG / multilingual_analysis
  [NeurIPS 2024] How do Large Language Models Handle Multilingualism?
  ☆34Updated 6 months ago
• princeton-nlp / Edge-Pruning
  [NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".
  ☆56Updated 2 months ago
• architsharma97 / dpo-rlaif
  ☆97Updated 11 months ago
• MikaStars39 / FeatureAlignment
  FeatureAlignment = Alignment + Mechanistic Interpretability
  ☆28Updated 2 months ago
• hannamw / EAP-IG
  ☆34Updated 2 weeks ago
• tim-lawson / mlsae
  Multi-Layer Sparse Autoencoders (ICLR 2025)
  ☆22Updated 3 months ago
• ryoungj / BoLT
  Code for "Reasoning to Learn from Latent Thoughts"
  ☆104Updated 2 months ago
• sail-sg / Attention-Sink
  [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)
  ☆85Updated 7 months ago
• alisawuffles / proxy-tuning
  Code associated with Tuning Language Models by Proxy (Liu et al., 2024)
  ☆110Updated last year
• IBM / activation-steering
  General-purpose activation steering library
  ☆75Updated 3 weeks ago
• activatedgeek / calibration-tuning
  ☆51Updated last month
• bartbussmann / matryoshka_sae
  ☆33Updated 4 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆65Updated last month
• hbin0701 / Self-Explore
  [𝐄𝐌𝐍𝐋𝐏 𝐅𝐢𝐧𝐝𝐢𝐧𝐠𝐬 𝟐𝟎𝟐𝟒 & 𝐀𝐂𝐋 𝟐𝟎𝟐𝟒 𝐍𝐋𝐑𝐒𝐄 𝐎𝐫𝐚𝐥] 𝘌𝘯𝘩𝘢𝘯𝘤𝘪𝘯𝘨 𝘔𝘢𝘵𝘩𝘦𝘮𝘢𝘵𝘪𝘤𝘢𝘭 𝘙𝘦𝘢𝘴𝘰𝘯𝘪𝘯…
  ☆51Updated last year
• jacobdunefsky / transcoder_circuits
  ☆124Updated 6 months ago
• joeljang / RLPHF
  Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging
  ☆106Updated last year