Code for reproducing our paper "Are Sparse Autoencoders Useful? A Case Study in Sparse Probing"
☆33Mar 31, 2025Updated last year
Alternatives and similar repositories for SAE-Probes
Users that are interested in SAE-Probes 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 reproducing our paper "Low Rank Adapting Models for Sparse Autoencoder Features"☆17Mar 31, 2025Updated last year
- Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"☆23Feb 6, 2025Updated last year
- ☆178May 1, 2026Updated 2 months ago
- Official Repository of Paper "Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs"☆15Sep 25, 2025Updated 10 months ago
- Let's try to reproduce the Golden Gate Claude demo, but using open-source Llama 3.1 8B, and the Eiffel Tower.☆19Nov 26, 2025Updated 8 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆27Jun 9, 2026Updated last month
- A tiny easily hackable implementation of a feature dashboard.☆17Oct 21, 2025Updated 9 months ago
- Code for "Physics Steering: Causal Control of Cross-Domain Concepts in a Physics Foundation Model" paper.☆15Mar 3, 2026Updated 4 months ago
- DESSERT Effeciently Searches Sets of Embeddings via Retrieval Tables☆18Feb 21, 2024Updated 2 years ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆58Oct 30, 2025Updated 8 months ago
- A fast high dimensional near neighbor search algorithm based on group testing and locality sensitive hashing☆23Dec 9, 2023Updated 2 years ago
- ☆15Jun 17, 2025Updated last year
- ☆211Nov 17, 2024Updated last year
- Linear Relational Embeddings (LREs) and Linear Relational Concepts (LRCs) for LLMs in PyTorch☆11Aug 7, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆48Sep 29, 2024Updated last year
- Sparsify transformers with SAEs and transcoders☆734Updated this week
- ☆15Jan 20, 2026Updated 6 months ago
- Official code for paper "Revisiting Model Interpolation for Efficient Reasoning"☆17Jul 14, 2026Updated last week
- Sparse autoencoders for vision☆64Updated this week
- Training Sparse Autoencoders on Language Models☆1,484Updated this week
- Exports Apple Notes into Markdown using Rust and AppleScript☆16Mar 4, 2026Updated 4 months ago
- ☆19Mar 3, 2025Updated last year
- Subliminal learning in LLMs: language models can transmit hidden preferences through seemingly unrelated training data.☆25Nov 9, 2025Updated 8 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆223Oct 14, 2025Updated 9 months ago
- All-in-one repository for Fine-tuning & Pretraining (Large) Language Models☆15Mar 8, 2023Updated 3 years ago
- ☆17Jul 31, 2025Updated 11 months ago
- Official code release for Delta Activations: A Representation for Finetuned Large Language Models☆20Sep 5, 2025Updated 10 months ago
- Pile Deduplication Code☆18May 15, 2023Updated 3 years ago
- A Swag Toggle for React Native and Expo Web☆14Jul 18, 2023Updated 3 years ago
- From pixels to symbolic rule learning☆12Nov 12, 2021Updated 4 years ago
- [NeurIPS 2025] Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models☆89Jun 5, 2026Updated last month
- RENT (Reinforcement Learning via Entropy Minimization) is an unsupervised method for training reasoning LLMs.☆42Oct 31, 2025Updated 8 months ago
- 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.
- Steering Vector Repo from "Extracting Latent Steering Vectors from Pretrained Language Models" - ACL2022 Findings☆11Mar 14, 2022Updated 4 years ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆268Updated this week
- Open Character Training☆92Apr 4, 2026Updated 3 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆210Mar 12, 2026Updated 4 months ago
- Code for the ICLR 2019 paper "Learning to Represent Edits"☆13Dec 8, 2022Updated 3 years ago
- ☆68Mar 27, 2025Updated last year
- Compress conventional Vision-Language Pre-training data☆52Sep 22, 2023Updated 2 years ago