mishajw / repengLinks
Experiments with representation engineering
☆12Updated last year
Alternatives and similar repositories for repeng
Users that are interested in repeng are comparing it to the libraries listed below
Sorting:
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆19Updated 11 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆97Updated 2 years ago
- A library for efficient patching and automatic circuit discovery.☆76Updated 2 months ago
- Steering Llama 2 with Contrastive Activation Addition☆180Updated last year
- ☆242Updated 11 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆124Updated 7 months ago
- Algebraic value editing in pretrained language models☆66Updated last year
- ☆127Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆19Updated 8 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆41Updated 7 months ago
- Unified access to Large Language Model modules using NNsight☆47Updated last week
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆211Updated last week
- Sparse Autoencoder Training Library☆54Updated 4 months ago
- Utilities for the HuggingFace transformers library☆72Updated 2 years ago
- Sparse probing paper full code.☆60Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆220Updated 9 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated this week
- ☆185Updated 2 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆72Updated last year
- ☆171Updated 10 months ago
- Attribution-based Parameter Decomposition☆30Updated 3 months ago
- Mechanistic Interpretability Visualizations using React☆289Updated 9 months ago
- Mechanistic Interpretability for Transformer Models☆51Updated 3 years ago
- ☆71Updated 3 weeks ago
- Erasing concepts from neural representations with provable guarantees☆234Updated 8 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆54Updated 11 months ago
- ☆23Updated last year
- ☆29Updated last year