rachtibat / LRP-eXplains-TransformersLinks
Layer-wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]
☆189Updated 2 months ago
Alternatives and similar repositories for LRP-eXplains-Transformers
Users that are interested in LRP-eXplains-Transformers are comparing it to the libraries listed below
Sorting:
- An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximization☆130Updated last year
- ☆32Updated 9 months ago
- A toolkit for quantitative evaluation of data attribution methods.☆53Updated 2 months ago
- Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.☆233Updated last month
- Using sparse coding to find distributed representations used by neural networks.☆269Updated last year
- [NeurIPS 2024] CoSy is an automatic evaluation framework for textual explanations of neurons.☆17Updated 3 months ago
- MetaQuantus is an XAI performance tool to identify reliable evaluation metrics☆39Updated last year
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆48Updated 10 months ago
- Mechanistic understanding and validation of large AI models with SemanticLens☆31Updated this week
- Official Code Implementation of the paper : XAI for Transformers: Better Explanations through Conservative Propagation☆64Updated 3 years ago
- A resource repository for representation engineering in large language models☆136Updated 10 months ago
- ☆121Updated this week
- This repository collects all relevant resources about interpretability in LLMs☆372Updated 10 months ago
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆76Updated 11 months ago
- A Python Data Valuation Package☆30Updated 2 years ago
- Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Works…☆19Updated last year
- A fast, effective data attribution method for neural networks in PyTorch☆217Updated 10 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆265Updated last year
- A simple PyTorch implementation of influence functions.☆91Updated last year
- A repository for summaries of recent explainable AI/Interpretable ML approaches☆83Updated 11 months ago
- Conformal Language Modeling☆32Updated last year
- A basic implementation of Layer-wise Relevance Propagation (LRP) in PyTorch.☆96Updated 2 years ago
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆104Updated 2 years ago
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023☆84Updated last year
- ☆345Updated last month
- 👋 Overcomplete is a Vision-based SAE Toolbox☆79Updated last month
- ☆26Updated 10 months ago
- [ICLR 23] A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled c…☆112Updated last year
- Materials for EACL2024 tutorial: Transformer-specific Interpretability☆60Updated last year
- Editing Models with Task Arithmetic☆500Updated last year