koayon / atp_star
PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
☆12Updated 5 months ago
Related projects: ⓘ
- ☆33Updated 3 months ago
- Mechanistic Interpretability for Transformer Models☆48Updated 2 years ago
- ☆75Updated this week
- A library for efficient patching and automatic circuit discovery.☆18Updated 3 weeks ago
- Universal Neurons in GPT2 Language Models☆25Updated 3 months ago
- ☆24Updated 5 months ago
- ☆48Updated 4 months ago
- ☆54Updated last week
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆22Updated 3 months ago
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆16Updated 6 months ago
- Repository for "I am a Strange Dataset: Metalinguistic Tests for Language Models"☆34Updated 8 months ago
- ☆99Updated 10 months ago
- Utilities for the HuggingFace transformers library☆55Updated last year
- A library for mechanistic anomaly detection☆13Updated this week
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆57Updated 10 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆57Updated last week
- ☆12Updated last week
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆88Updated 2 years ago
- we got you bro☆32Updated last month
- Sparse Autoencoder Training Library☆18Updated last month
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆14Updated 8 months ago
- Sparse and discrete interpretability tool for neural networks☆51Updated 7 months ago
- ☆59Updated last year
- ☆20Updated last year
- ☆50Updated last year
- ☆13Updated this week
- Steering Llama 2 with Contrastive Activation Addition☆83Updated 3 months ago
- ☆47Updated 3 months ago
- ☆68Updated 7 months ago
- Language-annotated Abstraction and Reasoning Corpus☆76Updated last year