interpretingdl / eacl2024_transformer_interpretability_tutorialLinks
Materials for EACL2024 tutorial: Transformer-specific Interpretability
☆60Updated last year
Alternatives and similar repositories for eacl2024_transformer_interpretability_tutorial
Users that are interested in eacl2024_transformer_interpretability_tutorial are comparing it to the libraries listed below
Sorting:
- This repository collects all relevant resources about interpretability in LLMs☆372Updated 10 months ago
- Sparse probing paper full code.☆60Updated 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
- ☆51Updated last month
- The geometry of multilingual language model representations (EMNLP 2022).☆21Updated 2 years ago
- Interpretability for sequence generation models 🐛 🔍☆438Updated this week
- Measuring the Mixing of Contextual Information in the Transformer☆31Updated 2 years ago
- ☆81Updated 6 months ago
- ☆122Updated last year
- ☆190Updated 9 months ago
- DecompX: Explaining Transformers Decisions by Propagating Token Decomposition [ACL 2023]☆18Updated 2 months ago
- ☆26Updated 7 months ago
- Using sparse coding to find distributed representations used by neural networks.☆269Updated last year
- A Python library that encapsulates various methods for neuron interpretation and analysis in Deep NLP models.☆105Updated last year
- ☆121Updated this week
- ☆240Updated 11 months ago
- ACL 2022: An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models.☆146Updated last month
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆54Updated 11 months ago
- ☆168Updated 10 months ago
- ☆26Updated 10 months ago
- How do transformer LMs encode relations?☆53Updated last year
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆162Updated 2 months ago
- ☆55Updated 2 years ago
- Code repository for the paper "Mission: Impossible Language Models."☆54Updated 4 months ago
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆41Updated 7 months ago
- Steering Llama 2 with Contrastive Activation Addition☆180Updated last year
- Resources for cultural NLP research☆103Updated 4 months ago
- ☆107Updated 7 months ago
- PAIR.withgoogle.com and friend's work on interpretability methods☆202Updated last week
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆147Updated this week