☆25Apr 23, 2024Updated 2 years ago
Alternatives and similar repositories for mats_sae_training_for_ViTs
Users that are interested in mats_sae_training_for_ViTs are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆60Nov 3, 2024Updated last year
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆15Feb 13, 2023Updated 3 years ago
- MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing…☆10Oct 7, 2024Updated last year
- ☆61Nov 19, 2024Updated last year
- ☆25Jan 28, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…☆25Feb 16, 2026Updated 5 months ago
- Time series data contribution via influence functions☆17Jan 18, 2025Updated last year
- PyTorch code and models for the DINOv2 self-supervised learning method.☆12Nov 12, 2023Updated 2 years ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆68Oct 27, 2024Updated last year
- A tiny easily hackable implementation of a feature dashboard.☆17Oct 21, 2025Updated 9 months ago
- ☆18Mar 4, 2024Updated 2 years ago
- ☆17Feb 14, 2024Updated 2 years ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- source code for NeurIPS'24 paper "Towards Calibrated Robust Fine-Tuning of Vision-Language Models"☆15Oct 31, 2025Updated 9 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆33Nov 11, 2025Updated 9 months ago
- ☆18Updated this week
- ☆28Mar 21, 2024Updated 2 years ago
- Applying SAEs for fine-grained control☆27Dec 15, 2024Updated last year
- ☆26Aug 23, 2025Updated 11 months ago
- Legacy-Bench: A benchmark for evaluating AI agents on legacy software engineering tasks☆19Jul 30, 2026Updated 2 weeks ago
- Training Sparse Autoencoders on Language Models☆1,501Updated this week
- A library for training crosscoders☆18May 28, 2025Updated last year
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆24Oct 18, 2024Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆27Oct 6, 2024Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆29Nov 20, 2024Updated last year
- AVocaDo : Strategy for Adapting Vocabulary to Downstream Domain☆23May 31, 2022Updated 4 years ago
- ☆429Aug 21, 2025Updated 11 months ago
- Sparsify transformers with SAEs and transcoders☆734Updated this week
- Code and results accompanying our paper titled RLSbench: Domain Adaptation under Relaxed Label Shift☆35Jul 19, 2023Updated 3 years ago
- Code for "Evidence of Learned Look-Ahead in a Chess-Playing Neural Network"☆31Jun 4, 2024Updated 2 years ago
- [EMNLP2025] Remedy: Learning Machine Translation Evaluation from Human Preferences with Reward Modeling☆16Nov 20, 2025Updated 8 months ago
- Scripts to generate and analyze afdb clusters☆11Sep 15, 2023Updated 2 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Official implementation of CytoSAE: Interpretable Cell Embeddings for Hematology☆27Jul 17, 2025Updated last year
- ☆182May 1, 2026Updated 3 months ago
- Markdown that runs — one file, any agent.☆65Updated this week
- Algebraic value editing in pretrained language models☆71Nov 1, 2023Updated 2 years ago
- ☆67Feb 16, 2023Updated 3 years ago
- an universal pytorch deep learning experiment codebase☆11Mar 31, 2025Updated last year
- Sparse Autoencoders (SAE) vs CLIP fine-tuning fun.☆18Dec 19, 2024Updated last year