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 paper "Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 Small"
☆14Jan 26, 2025Updated last year
Alternatives and similar repositories for SAE-Ravel
Users that are interested in SAE-Ravel are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆58Oct 30, 2025Updated 11 months ago
- A benchmark for mechanistic discovery of circuits in Transformers☆18Dec 15, 2024Updated last year
- A library for mechanistic anomaly detection☆22Jan 9, 2025Updated last year
- ☆30Aug 2, 2024Updated 2 years ago
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆60Nov 3, 2024Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆186May 1, 2026Updated 5 months ago
- Applying SAEs for fine-grained control☆28Dec 15, 2024Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆21Jan 19, 2025Updated last year
- ☆35Sep 13, 2023Updated 3 years ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆34May 23, 2024Updated 2 years ago
- This repository contains the code used for the experiments in the paper "Language Models use Lookbacks to Track Beliefs".☆17Mar 14, 2026Updated 7 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆164Feb 21, 2025Updated last year
- Attribution-based Parameter Decomposition☆35Jun 11, 2025Updated last year
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet☆32Aug 22, 2023Updated 3 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆10Mar 24, 2025Updated last year
- ☆17Feb 14, 2024Updated 2 years ago
- ☆15May 15, 2026Updated 5 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆30Nov 20, 2024Updated last year
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆30Feb 6, 2026Updated 8 months ago
- Tools for running experiments on RL agents in procgen environments☆19Apr 5, 2024Updated 2 years ago
- ☆17Jul 6, 2020Updated 6 years ago
- ☆13Aug 19, 2024Updated 2 years ago
- ☆105Oct 30, 2023Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆25Dec 11, 2024Updated last year
- This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)☆28Sep 10, 2024Updated 2 years ago
- ☆10Aug 25, 2020Updated 6 years ago
- ☆298Oct 1, 2024Updated 2 years ago
- ☆18Jun 3, 2026Updated 4 months ago
- ☆434Aug 21, 2025Updated last year
- ☆21May 1, 2025Updated last year
- Collection of Reverse Engineering in Large Model☆35Jan 8, 2025Updated last year
- [ICLR 2025] On Evluating the Durability of Safegurads for Open-Weight LLMs☆13Jun 20, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [NeurIPS XAIA & Springer] Code and notebooks to paper "A Fresh Look at Sanity Checks for Saliency Maps"☆25Jul 12, 2024Updated 2 years ago
- Identification of the Adversary from a Single Adversarial Example (ICML 2023)☆10Jul 15, 2024Updated 2 years ago
- [AAAI26] Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilitie…☆11Feb 7, 2026Updated 8 months ago
- ☆12Apr 19, 2022Updated 4 years ago
- ☆26Aug 23, 2025Updated last year
- This is the implementation of CounterCurate, the data curation pipeline of both physical and semantic counterfactual image-caption pairs.☆19Jun 27, 2024Updated 2 years ago
- Mapping out the "memory" of neural nets with data attribution☆101Updated this week