EleutherAI / w2sLinks
☆23Updated 11 months ago
Alternatives and similar repositories for w2s
Users that are interested in w2s are comparing it to the libraries listed below
Sorting:
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆77Updated 5 months ago
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆160Updated 2 months ago
- ☆226Updated last year
- ☆96Updated last year
- Augmenting Statistical Models with Natural Language Parameters☆27Updated 11 months ago
- Sparse probing paper full code.☆60Updated last year
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆74Updated 11 months ago
- [ICLR 2025] General-purpose activation steering library☆99Updated last week
- ☆238Updated last year
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆95Updated 4 years ago
- ☆44Updated last year
- A fast, effective data attribution method for neural networks in PyTorch☆217Updated 9 months ago
- ☆106Updated 6 months ago
- AI Logging for Interpretability and Explainability🔬☆124Updated last year
- ☆25Updated 6 months ago
- Algebraic value editing in pretrained language models☆65Updated last year
- `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.☆84Updated 2 months ago
- ☆51Updated last year
- ☆122Updated last year
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆41Updated 6 months ago
- 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 7 months ago
- ☆65Updated 2 years ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆53Updated 11 months ago
- ☆47Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆178Updated last year
- A library for efficient patching and automatic circuit discovery.☆76Updated last month
- ☆165Updated 9 months ago
- Using sparse coding to find distributed representations used by neural networks.☆265Updated last year
- A resource repository for representation engineering in large language models☆132Updated 9 months ago
- ☆73Updated 3 years ago