Efficient Dictionary Learning with Switch Sparse Autoencoders (SAEs)
☆26Dec 1, 2024Updated last year
Alternatives and similar repositories for switch_sae
Users that are interested in switch_sae are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆26Aug 23, 2025Updated last year
- Code for "In-Context Former: Lightning-fast Compressing Context for Large Language Model" (Findings of EMNLP 2024)☆21Nov 21, 2024Updated last year
- ☆21Nov 3, 2024Updated last year
- ☆16Jul 15, 2025Updated last year
- Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"☆23Feb 6, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Trains Sparse Autoencoders based on outputs from language models☆11Oct 7, 2024Updated 2 years ago
- ☆434Aug 21, 2025Updated last year
- The official code of On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment☆28May 13, 2026Updated 4 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆30Nov 20, 2024Updated last year
- ☆16Jan 2, 2026Updated 9 months ago
- [ICLR 2026] A framework to "create benchmarks" and "evaluate AI co-scientists" in experimental data-driven real-world scientific research…☆21Sep 14, 2026Updated 3 weeks ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆279Updated this week
- Scratchpad/Chain-of-Thought Prompts☆12Jun 6, 2022Updated 4 years ago
- Realign is a testing and simulation framework for AI applications.☆19Dec 4, 2024Updated last year
- 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.
- A python implementation of PROCLUS: PROjected CLUStering algorithm.☆10Jan 12, 2015Updated 11 years ago
- Recommendation engine and it's algorithms in python , R .☆12Oct 26, 2018Updated 7 years ago
- [EMNLP 25] An effective and interpretable weight-editing method for mitigating overly short reasoning in LLMs, and a mechanistic study un…☆20Aug 24, 2026Updated last month
- ArXiv'18 implementation of amortized maximum likelihood (AML) for high-quality, weakly-supervised shape completion.☆11Nov 30, 2018Updated 7 years ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆30Feb 6, 2026Updated 8 months ago
- Mac port of Torcs, The Open Racing Car Simulator☆12Jun 16, 2010Updated 16 years ago
- ☆14Apr 27, 2022Updated 4 years ago
- ☆21Jul 9, 2025Updated last year
- ☆10Jul 4, 2024Updated 2 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Fluent dreaming for language models☆13Jul 22, 2024Updated 2 years ago
- [NeurIPS'23] Binary Classification with Confidence Difference☆10May 13, 2024Updated 2 years ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆276Feb 27, 2026Updated 7 months ago
- ☆11Mar 31, 2022Updated 4 years ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated 2 years ago
- An implementation of the paper "Learning to Reweight Examples for Robust Deep Learning" from ICML 2018 with PyTorch and Higher.☆28Oct 11, 2022Updated 4 years ago
- ☆12Oct 23, 2022Updated 3 years ago
- ☆15Mar 30, 2025Updated last year
- ☆74Jan 17, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [JMLR] Gradual Domain Adaptation: Theory and Algorithms☆11Jan 14, 2025Updated last year
- [ICML 2023] Protecting Language Generation Models via Invisible Watermarking☆13Sep 8, 2023Updated 3 years ago
- FeatureAlignment = Alignment + Mechanistic Interpretability☆35Mar 8, 2025Updated last year
- ☆16May 30, 2024Updated 2 years ago
- Repository for the NeurIPS 2023 paper "Beyond Confidence: Reliable Models Should Also Consider Atypicality"☆13Apr 21, 2024Updated 2 years ago
- [AAAI26] Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilitie…☆11Feb 7, 2026Updated 8 months ago
- ☆11Mar 20, 2023Updated 3 years ago