This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper accepted at the ICCV CLVL Workshop 2023
☆25Feb 16, 2026Updated 3 months ago
Alternatives and similar repositories for Towards-Vision-Language-Mechanistic-Interpretability
Users that are interested in Towards-Vision-Language-Mechanistic-Interpretability are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Applying SAEs for fine-grained control☆27Dec 15, 2024Updated last year
- ☆13Apr 10, 2025Updated last year
- ☆17Jun 19, 2023Updated 2 years ago
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆13Feb 13, 2023Updated 3 years ago
- [ICML 24] A novel automated neuron explanation framework that can accurately describe poly-semantic concepts in deep neural networks☆14May 2, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆14Feb 24, 2025Updated last year
- Experiments with representation engineering☆14Feb 28, 2024Updated 2 years ago
- ☆30May 4, 2023Updated 3 years ago
- ☆25Apr 23, 2024Updated 2 years ago
- BCQ tutorial for transformers☆16Jul 17, 2023Updated 2 years ago
- Code base for paper "Finding Structural Knowledge in Multimodal-BERT". Framework for probing and code for creating Scene Trees.☆10May 19, 2022Updated 4 years ago
- ☆19Mar 5, 2024Updated 2 years ago
- ☆51Oct 23, 2023Updated 2 years ago
- See https://github.com/cuda-mode/triton-index/ instead!☆11May 8, 2024Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Works…☆20May 29, 2024Updated last year
- ☆17Feb 14, 2024Updated 2 years ago
- [Science Advances] Demographic Bias of Vision-Language Foundation Models in Medical Imaging☆21Mar 28, 2025Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- A Mechanistic Interpretability Analysis of Grokking☆27Sep 26, 2022Updated 3 years ago
- ☆18May 18, 2026Updated last week
- Code for reproducing our paper "Low Rank Adapting Models for Sparse Autoencoder Features"☆17Mar 31, 2025Updated last year
- ☆73May 7, 2026Updated 2 weeks ago
- Interpreting CLIP with Hierarchical Sparse Autoencoders (ICML 2025)☆26Jan 17, 2026Updated 4 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Code for "Evidence of Learned Look-Ahead in a Chess-Playing Neural Network"☆29Jun 4, 2024Updated last year
- Extensive Self-Contrast Enables Feedback-Free Language Model Alignment☆20Apr 2, 2024Updated 2 years ago
- ☆13Sep 8, 2024Updated last year
- Official implementation for NeurIPS'23 paper "Geodesic Multi-Modal Mixup for Robust Fine-Tuning"☆35Sep 24, 2024Updated last year
- ☆12Dec 15, 2023Updated 2 years ago
- A toolkit for scaling law research ⚖☆63Jan 27, 2025Updated last year
- ☆247Nov 22, 2024Updated last year
- Emotiv SDK Community Edition☆13Oct 9, 2015Updated 10 years ago
- ☆13Jul 1, 2024Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?☆43Nov 1, 2024Updated last year
- [UNDER CONSTRUCTION]unofficial implementation of ABC-Net☆12Feb 5, 2018Updated 8 years ago
- A library of visualization tools for the interpretability and hallucination analysis of large vision-language models (LVLMs).☆42May 22, 2025Updated last year
- Xie's R Archive Network (experimental and for my personal interest only)☆26Sep 6, 2021Updated 4 years ago
- ☆14Jun 24, 2024Updated last year
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆24Oct 18, 2024Updated last year
- ☆31Aug 18, 2025Updated 9 months ago