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 8 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.☆12Updated this week
- ☆13Updated this week
- A library for efficient patching and automatic circuit discovery.☆67Updated 2 months ago
- ☆13Updated 2 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 5 months ago
- ☆28Updated last year
- Sparse Autoencoder Training Library☆52Updated last month
- ☆37Updated last month
- ☆31Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆35Updated last year
- Engine for collecting, uploading, and downloading model activations☆18Updated 2 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆75Updated 7 months ago
- Experiments with representation engineering☆11Updated last year
- graphpatch is a library for activation patching on PyTorch neural network models.☆16Updated 4 months ago
- Applying SAEs for fine-grained control☆19Updated 6 months ago
- ☆57Updated last week
- A small package implementing some useful wrapping around nnsight☆13Updated this week
- Modified to support crosscoder training.☆17Updated this week
- A TinyStories LM with SAEs and transcoders☆11Updated 2 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆110Updated 4 months ago
- How do transformer LMs encode relations?☆49Updated last year
- A python sdk for LLM finetuning and inference on runpod infrastructure☆11Updated last week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆187Updated this week
- ☆99Updated 4 months ago
- ☆121Updated last year
- Mechanistic Interpretability for Transformer Models☆51Updated 3 years ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆202Updated 6 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 8 months ago
- ☆134Updated 7 months ago
- Measuring the situational awareness of language models☆35Updated last year