Erasing concepts from neural representations with provable guarantees
☆271Jan 27, 2025Updated last year
Alternatives and similar repositories for concept-erasure
Users that are interested in concept-erasure are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆39Jul 14, 2022Updated 4 years ago
- ☆12Oct 23, 2022Updated 4 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆226Oct 26, 2026Updated last week
- ☆292Mar 2, 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
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Tools for understanding how transformer predictions are built layer-by-layer☆619Aug 7, 2025Updated last year
- Minimum Description Length probing for neural network representations☆20Jan 28, 2025Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆21Jan 19, 2025Updated last year
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated 2 years ago
- Closed-form polynomial approximations to neural networks☆13Jan 31, 2025Updated last year
- Algebraic value editing in pretrained language models☆73Nov 1, 2023Updated 3 years ago
- ☆95Jun 6, 2022Updated 4 years ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆914Mar 6, 2026Updated 7 months ago
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆15Feb 13, 2023Updated 3 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Understanding how features learned by neural networks evolve throughout training☆40Oct 24, 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 …☆280Updated this week
- ☆58Jun 15, 2023Updated 3 years ago
- Mechanistic Interpretability Visualizations using React☆372Apr 30, 2026Updated 6 months ago
- Quantifying degeneracy in toy models☆11Sep 6, 2024Updated 2 years ago
- Code for 'The Linear Representation Hypothesis and the Geometry of Large Language Models' (ICML 2024)☆135Feb 11, 2025Updated last year
- A library for mechanistic interpretability of GPT-style language models☆4,031Updated this week
- Sparsify transformers with SAEs and transcoders☆742Updated this week
- ☆301Oct 1, 2024Updated 2 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Sparse Autoencoder Training Library☆59May 1, 2025Updated last year
- A tiny easily hackable implementation of a feature dashboard.☆18Oct 21, 2025Updated last year
- ☆570Feb 5, 2024Updated 2 years ago
- CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior☆13Sep 21, 2022Updated 4 years ago
- ☆45Nov 17, 2024Updated last year
- Training Sparse Autoencoders on Language Models☆1,579Oct 20, 2026Updated 2 weeks ago
- ☆19Mar 5, 2024Updated 2 years ago
- ☆186May 1, 2026Updated 6 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆74Jun 19, 2024Updated 2 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- suffix array construction and searching algorithms for in-memory binary data.☆13Sep 10, 2022Updated 4 years ago
- ☆30Aug 2, 2024Updated 2 years ago
- SAEs in Jax☆12Dec 16, 2024Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆30Nov 20, 2024Updated last year
- ☆48Feb 8, 2025Updated last year
- A library for efficient patching and automatic circuit discovery.☆103Aug 17, 2026Updated 2 months ago
- gpt completions in vscode☆35Mar 24, 2023Updated 3 years ago