atticusg / CausalAbstractionLinks
☆22Updated last month
Alternatives and similar repositories for CausalAbstraction
Users that are interested in CausalAbstraction are comparing it to the libraries listed below
Sorting:
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆54Updated 11 months ago
- Unified access to Large Language Model modules using NNsight☆44Updated this 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 7 months ago
- Sparse probing paper full code.☆60Updated last year
- Landing page for MIB: A Mechanistic Interpretability Benchmark☆19Updated last month
- ☆91Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆19Updated 8 months ago
- A library for efficient patching and automatic circuit discovery.☆76Updated 2 months ago
- ☆107Updated 7 months ago
- Algebraic value editing in pretrained language models☆66Updated last year
- ☆81Updated 6 months ago
- Code repository for the paper "Mission: Impossible Language Models."☆54Updated 4 months ago
- ☆18Updated last month
- ☆171Updated 10 months ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆12Updated last year
- [ICLR 2025] General-purpose activation steering library☆105Updated this week
- How do transformer LMs encode relations?☆53Updated last year
- ☆123Updated last year
- ☆17Updated 5 months ago
- ☆51Updated last month
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 10 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆79Updated last year
- A benchmark for mechanistic discovery of circuits in Transformers☆15Updated 9 months ago
- ☆26Updated 7 months ago
- Materials for EACL2024 tutorial: Transformer-specific Interpretability☆60Updated last year
- Attribution-based Parameter Decomposition☆30Updated 3 months ago
- ☆185Updated 2 months ago
- Modified to support crosscoder training.☆23Updated last month
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆41Updated last year
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆96Updated 4 years ago