Training code for Sparse Autoencoders on Embedding models
☆40Jul 11, 2026Updated last month
Alternatives and similar repositories for latent-sae
Users that are interested in latent-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:
- Using modal.com to process FineWeb-edu data☆20Apr 11, 2026Updated 4 months ago
- The training codes of Jasper-Token-Compression-600M☆20Nov 19, 2025Updated 9 months ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated 2 years ago
- MEXMA: Token-level objectives improve sentence representations☆44Jan 6, 2025Updated last year
- ☆14Jul 7, 2024Updated 2 years 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.
- GPT-jax based on the official huggingface library☆13Jun 22, 2021Updated 5 years ago
- Sparsify transformers with SAEs and transcoders☆734Aug 10, 2026Updated last week
- A simple, yet comprehensive foundation for interacting with common cloud providers in Julia (GCP, Azure, AWS).☆20Aug 6, 2026Updated last week
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆19Jul 24, 2025Updated last year
- Find all variables referenced and assigned in an expression☆17Updated this week
- Simple Transformer in Jax☆143Jun 22, 2024Updated 2 years ago
- Structured protocol for AI coding agents to debate technical decisions via shared markdown☆15Aug 3, 2026Updated 2 weeks ago
- Sampling-Based Minimum Bayes-Risk Decoding for Neural Machine Translation☆16Oct 14, 2022Updated 3 years ago
- Sparse Autoencoder Training Library☆58May 1, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- An introduction to LLM Sampling☆80Dec 15, 2024Updated last year
- Sparse Autoencoders (SAE) vs CLIP fine-tuning fun.☆18Dec 19, 2024Updated last year
- https://footprints.baulab.info☆17Oct 4, 2024Updated last year
- ☆28Oct 7, 2025Updated 10 months ago
- Code for the paper "Multi-Field Adaptive Retrieval," a research project on a semi-structured document retrieval☆18Feb 13, 2026Updated 6 months ago
- Modal LLM LLama.cpp based model deployment as part of series of Model as a Service (MaaS)☆17Mar 23, 2026Updated 4 months ago
- ☆12Dec 28, 2021Updated 4 years ago
- A sample pattern for running CI tests on Modal☆19Apr 12, 2025Updated last year
- A webhook that integrates the W&B model registry with Modal Labs☆15Dec 24, 2023Updated 2 years ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- ☆33Updated this week
- KoCommonGEN v2: A Benchmark for Navigating Korean Commonsense Reasoning Challenges in Large Language Models☆25Aug 24, 2024Updated last year
- utilities for loading and running text embeddings with onnx☆46Aug 16, 2025Updated last year
- Word sense disambiguation test sets for NMT☆21Dec 3, 2020Updated 5 years ago
- ☆18Jun 19, 2023Updated 3 years ago
- ☆63Jan 26, 2025Updated last year
- Orchestrate Modal and OpenAI workloads with Dagster☆13Dec 11, 2024Updated last year
- code for training & evaluating Contextual Document Embedding models☆207May 14, 2025Updated last year
- Implementation and explorations into DiscoRL, Discovering state-of-the-art reinforcement learning algorithms, David Silver's last work at…☆21Jun 13, 2026Updated 2 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.
- Code & data for EMNLP 2020 paper "MOCHA: A Dataset for Training and Evaluating Reading Comprehension Metrics".☆16May 3, 2022Updated 4 years ago
- BPE modification that implements removing of the intermediate tokens during tokenizer training.☆27Nov 25, 2024Updated last year
- ☆25Mar 28, 2024Updated 2 years ago
- Privacy-preserving k-means clustering on data owned by multiple parties☆14May 10, 2016Updated 10 years ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆269Feb 27, 2026Updated 5 months ago
- 🚀 A simple, modern, full-stack toolkit for Python 🐍☆39Oct 18, 2024Updated last year
- run dreambooth training on modal☆22Nov 21, 2022Updated 3 years ago