adamkarvonen / dictionary_learning_demoLinks
☆15Updated this week
Alternatives and similar repositories for dictionary_learning_demo
Users that are interested in dictionary_learning_demo are comparing it to the libraries listed below
Sorting:
- ☆111Updated last month
- ☆47Updated last month
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆12Updated 6 months ago
- ☆103Updated 6 months ago
- [ICLR 2025] General-purpose activation steering library☆94Updated 3 weeks ago
- Sparse probing paper full code.☆59Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆53Updated 10 months ago
- ☆184Updated last month
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆76Updated 5 months ago
- A library for efficient patching and automatic circuit discovery.☆76Updated last month
- Steering Llama 2 with Contrastive Activation Addition☆174Updated last year
- ☆96Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆176Updated 4 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- Algebraic value editing in pretrained language models☆65Updated last year
- ☆60Updated 5 months ago
- ☆47Updated last year
- ☆162Updated 9 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆206Updated last week
- ☆223Updated last year
- ☆90Updated last year
- ☆38Updated 7 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆24Updated 9 months ago
- ☆122Updated last year
- ☆53Updated 2 years ago
- Code for "Automatic Circuit Finding and Faithfulness"☆14Updated last year
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆74Updated 10 months ago
- Using sparse coding to find distributed representations used by neural networks.☆262Updated last year
- Modified to support crosscoder training.☆21Updated 3 weeks ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆143Updated last week