ArthurConmy / MishformerLensLinks
MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing a custom, numerically inaccurate Transformer architecture.
☆10Updated 11 months ago
Alternatives and similar repositories for MishformerLens
Users that are interested in MishformerLens are comparing it to the libraries listed below
Sorting:
- A tiny easily hackable implementation of a feature dashboard.☆14Updated last week
- Sparse Autoencoder Training Library☆54Updated 4 months ago
- graphpatch is a library for activation patching on PyTorch neural network models.☆20Updated 7 months ago
- Erasing concepts from neural representations with provable guarantees☆234Updated 8 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆41Updated last year
- ☆15Updated 2 months ago
- Engine for collecting, uploading, and downloading model activations☆22Updated 5 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆19Updated 8 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆220Updated 9 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆124Updated 7 months ago
- ☆34Updated last year
- ☆127Updated last year
- How do transformer LMs encode relations?☆53Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆211Updated last week
- A library for efficient patching and automatic circuit discovery.☆76Updated 2 months ago
- Mechanistic Interpretability Visualizations using React☆289Updated 9 months ago
- ☆51Updated 2 months ago
- Extract full next-token probabilities via language model APIs☆248Updated last year
- A library for training crosscoders☆11Updated 4 months ago
- Attribution-based Parameter Decomposition☆30Updated 3 months ago
- ☆71Updated 3 weeks ago
- ☆242Updated 11 months ago
- ☆142Updated 2 weeks ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆19Updated last year
- A python sdk for LLM finetuning and inference on runpod infrastructure☆15Updated last week
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆80Updated 10 months ago
- ☆29Updated last year
- Repository for the code of the "PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided Decoding" paper, NAACL'22☆66Updated 2 years ago
- ☆109Updated 7 months ago
- Code for the paper "Fishing for Magikarp"☆165Updated 4 months ago