Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
☆58Oct 30, 2025Updated 10 months ago
Alternatives and similar repositories for ravel
Users that are interested in 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:
- 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…☆14Jan 26, 2025Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆214Mar 12, 2026Updated 5 months ago
- The codebase for Inducing Causal Structure for Interpretable Neural Networks☆11Dec 3, 2021Updated 4 years ago
- [ICLR 2025] "Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond"☆16Feb 27, 2025Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆85Jun 20, 2026Updated 2 months 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.
- A suite of interpretability tasks to evaluate agents using Scribe for notebook access☆18Oct 2, 2025Updated 11 months ago
- A benchmark for mechanistic discovery of circuits in Transformers☆18Dec 15, 2024Updated last year
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆899Mar 6, 2026Updated 6 months ago
- ADAG: Transluce's MLP neuron-level circuit tracing library☆37Apr 10, 2026Updated 4 months ago
- Attribution-based Parameter Decomposition☆35Jun 11, 2025Updated last year
- Code for 'The Linear Representation Hypothesis and the Geometry of Large Language Models' (ICML 2024)☆129Feb 11, 2025Updated last year
- [EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆39Aug 20, 2025Updated last year
- ☆224Oct 14, 2025Updated 10 months ago
- ☆113Updated this week
- 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.
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated 2 years ago
- Materials for "Multi-property Steering of Large Language Models with Dynamic Activation Composition"☆14Nov 22, 2024Updated last year
- Sparse probing paper full code.☆68Dec 17, 2023Updated 2 years ago
- ☆24Jun 13, 2024Updated 2 years ago
- ☆211Nov 17, 2024Updated last year
- Sparse Autoencoder Training Library☆58May 1, 2025Updated last year
- ☆36Nov 16, 2025Updated 9 months ago
- ☆428Aug 21, 2025Updated last year
- ☆33Nov 28, 2024Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆18Jul 9, 2025Updated last year
- ☆30Aug 2, 2024Updated 2 years ago
- The Codebase for Causal Distillation for Language Models (NAACL '22)☆26May 1, 2022Updated 4 years ago
- ☆257Feb 22, 2024Updated 2 years ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆275Aug 31, 2026Updated last week
- Exploring the Limitations of Large Language Models on Multi-Hop Queries☆33Mar 2, 2025Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆90Mar 7, 2025Updated last year
- A tiny easily hackable implementation of a feature dashboard.☆17Oct 21, 2025Updated 10 months ago
- ☆87Feb 18, 2026Updated 6 months ago
- 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.
- ☆19Mar 5, 2024Updated 2 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
- Steering Llama 2 with Contrastive Activation Addition☆250May 23, 2024Updated 2 years ago
- Official repo for NeurIPS'24 paper "WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models"☆19Dec 16, 2024Updated last year
- ☆22Nov 15, 2024Updated last year
- A library for efficient patching and automatic circuit discovery.☆102Aug 17, 2026Updated 3 weeks ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆30Nov 20, 2024Updated last year