mitvis / saliency-cards
Saliency Cards are transparency documentation for saliency methods. Learn about new saliency methods or document your own!
☆16Updated last year
Alternatives and similar repositories for saliency-cards:
Users that are interested in saliency-cards are comparing it to the libraries listed below
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆41Updated 2 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆95Updated 2 months ago
- ☆121Updated last year
- A library for efficient patching and automatic circuit discovery.☆62Updated 2 months ago
- Sparse probing paper full code.☆55Updated last year
- Erasing concepts from neural representations with provable guarantees☆227Updated 2 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆91Updated last year
- Experiments with representation engineering☆11Updated last year
- 🧠 Starter templates for doing interpretability research☆70Updated last year
- Inspecting and Editing Knowledge Representations in Language Models☆115Updated last year
- we got you bro☆35Updated 8 months ago
- ☆218Updated 6 months ago
- Mechanistic Interpretability for Transformer Models☆50Updated 2 years ago
- Attribution-based Parameter Decomposition☆17Updated this week
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆199Updated last week
- Sparse Autoencoder Training Library☆48Updated 5 months ago
- Universal Neurons in GPT2 Language Models☆27Updated 10 months ago
- ☆85Updated last week
- Mechanistic Interpretability Visualizations using React☆241Updated 4 months ago
- ☆41Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆68Updated 10 months ago
- A mechanistic approach for understanding and detecting factual errors of large language models.☆43Updated 9 months ago
- Tools for studying developmental interpretability in neural networks.☆88Updated 2 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆169Updated this week
- PAIR.withgoogle.com and friend's work on interpretability methods☆180Updated last week
- ☆90Updated 2 months ago
- Algebraic value editing in pretrained language models☆63Updated last year
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆74Updated last year
- ☆36Updated last month
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆43Updated 6 months ago