wesg52 / llm-context-neuronsLinks
Find context neurons in Pythia models.
☆14Updated 2 years ago
Alternatives and similar repositories for llm-context-neurons
Users that are interested in llm-context-neurons are comparing it to the libraries listed below
Sorting:
- Sparse probing paper full code.☆61Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆97Updated 2 years ago
- ☆173Updated 10 months ago
- ☆123Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆270Updated last year
- ☆242Updated last year
- ☆186Updated 2 months ago
- ☆51Updated 2 months ago
- Materials for EACL2024 tutorial: Transformer-specific Interpretability☆60Updated last year
- ☆125Updated 2 weeks ago
- Conformal Language Modeling☆32Updated last year
- ☆127Updated last year
- [ICLR 2025] General-purpose activation steering library☆107Updated 2 weeks ago
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆97Updated 4 years ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆54Updated 11 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆124Updated 7 months ago
- This repository collects all relevant resources about interpretability in LLMs☆373Updated 11 months ago
- Steering Llama 2 with Contrastive Activation Addition☆182Updated last year
- An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"☆49Updated last year
- A resource repository for representation engineering in large language models☆136Updated 10 months ago
- ☆106Updated 7 months ago
- ☆91Updated last year
- ☆199Updated 10 months ago
- A library for efficient patching and automatic circuit discovery.☆77Updated 2 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆268Updated last year
- Mechanistic Interpretability Visualizations using React☆289Updated 9 months ago
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆41Updated 7 months ago
- Algebraic value editing in pretrained language models☆66Updated last year
- 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
- ☆230Updated last year