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 10 months ago
- ☆238Updated 11 months ago
- ☆126Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆95Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 10 months ago
- A library for efficient patching and automatic circuit discovery.☆76Updated last month
- A tiny easily hackable implementation of a feature dashboard.☆12Updated 2 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆19Updated 7 months ago
- Steering Llama 2 with Contrastive Activation Addition☆178Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆121Updated 6 months ago
- ☆122Updated last year
- Algebraic value editing in pretrained language models☆65Updated last year
- ☆116Updated last month
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆207Updated this week
- Sparse Autoencoder Training Library☆54Updated 4 months ago
- Unified access to Large Language Model modules using NNsight☆44Updated last week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆214Updated 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
- Mechanistic Interpretability Visualizations using React☆282Updated 8 months ago
- ☆81Updated 6 months ago
- Utilities for the HuggingFace transformers library☆70Updated 2 years ago
- ☆165Updated 9 months ago
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆41Updated 6 months ago
- ☆90Updated last year
- Sparse probing paper full code.☆60Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆53Updated 10 months ago
- Attribution-based Parameter Decomposition☆29Updated 2 months ago
- ☆53Updated 9 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆24Updated 9 months ago