mlepori1 / NeuroSurgeonLinks
NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers
☆41Updated 5 months ago
Alternatives and similar repositories for NeuroSurgeon
Users that are interested in NeuroSurgeon are comparing it to the libraries listed below
Sorting:
- A library for efficient patching and automatic circuit discovery.☆73Updated 2 weeks ago
- ☆103Updated 5 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆52Updated 10 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- ☆234Updated 10 months ago
- ☆121Updated last year
- A fast, effective data attribution method for neural networks in PyTorch☆215Updated 8 months ago
- ☆62Updated 2 years ago
- Sparse probing paper full code.☆58Updated last year
- ☆81Updated 5 months ago
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆158Updated last month
- ☆47Updated last year
- ☆124Updated last year
- ☆96Updated last year
- ☆17Updated last week
- 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
- [ICLR 2025] General-purpose activation steering library☆87Updated last week
- ☆109Updated 3 weeks ago
- ☆60Updated 3 years ago
- ☆36Updated 3 years ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆202Updated this week
- ☆222Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆120Updated 5 months ago
- ☆183Updated 3 weeks ago
- Steering Llama 2 with Contrastive Activation Addition☆167Updated last year
- How do transformer LMs encode relations?☆52Updated last year
- Algebraic value editing in pretrained language models☆65Updated last year
- Experiments with representation engineering☆12Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆74Updated 5 months ago
- ☆89Updated last year