Training code for Sparse Autoencoders on Embedding models
☆39May 9, 2026Updated 3 weeks ago
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 last month
- The training codes of Jasper-Token-Compression-600M☆19Nov 19, 2025Updated 6 months ago
- Live-editable codeblocks for any language.☆16Dec 13, 2025Updated 5 months ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated last year
- MEXMA: Token-level objectives improve sentence representations☆43Jan 6, 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.
- ☆14Jul 7, 2024Updated last year
- Sparsify transformers with SAEs and transcoders☆721Updated this week
- ☆21Nov 18, 2024Updated last year
- Code for the paper "Multi-Field Adaptive Retrieval," a research project on a semi-structured document retrieval☆17Feb 13, 2026Updated 3 months ago
- An introduction to LLM Sampling☆80Dec 15, 2024Updated last year
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆19Jul 24, 2025Updated 10 months ago
- Finetune your embeddings in-browser☆35Apr 14, 2024Updated 2 years ago
- Simple Transformer in Jax☆143Jun 22, 2024Updated last year
- Find all variables referenced and assigned in an expression☆17May 1, 2026Updated 3 weeks 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.
- User-friendly viewer for Parquet files☆12May 8, 2026Updated 3 weeks ago
- Sparse Autoencoder Training Library☆57May 1, 2025Updated last year
- ☆63Jan 26, 2025Updated last year
- All-in-one RAG toolkit—from quick prototypes to advanced pipelines.☆32Nov 27, 2025Updated 6 months ago
- A toy text-to-image model trained from scratch.☆19Jun 9, 2025Updated 11 months ago
- Sparse Autoencoders (SAE) vs CLIP fine-tuning fun.☆18Dec 19, 2024Updated last year
- https://footprints.baulab.info☆18Oct 4, 2024Updated last year
- ☆17Jun 19, 2023Updated 2 years ago
- ☆12Dec 28, 2021Updated 4 years 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.
- A sample pattern for running CI tests on Modal☆19Apr 12, 2025Updated last year
- A collection of optimized ComfyUI-based cloud inference endpoints, built on ComfyDeploy and Modal☆16Nov 5, 2024Updated last year
- A webhook that integrates the W&B model registry with Modal Labs☆15Dec 24, 2023Updated 2 years ago
- ☆24Jan 28, 2025Updated last year
- KoCommonGEN v2: A Benchmark for Navigating Korean Commonsense Reasoning Challenges in Large Language Models☆25Aug 24, 2024Updated last year
- ☆18Apr 23, 2025Updated last year
- Because it's there.☆16Sep 22, 2024Updated last year
- Eden is building autonomous creative agents.☆30Apr 27, 2026Updated last month
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆49Nov 6, 2024Updated last year
- 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.
- BPE modification that implements removing of the intermediate tokens during tokenizer training.☆27Nov 25, 2024Updated last year
- code for training & evaluating Contextual Document Embedding models☆205May 14, 2025Updated last year
- Make running benchmark simple yet maintainable, again. Now only supports Korean-based cross-encoder.☆34Dec 2, 2025Updated 5 months ago
- Training hybrid models for dummies.☆30Nov 1, 2025Updated 6 months ago
- Well documented examples of running distributed training jobs on Modal☆28May 19, 2026Updated last week
- WIP Pytorch code for stably training single-step, mode-dropping, deterministic autoencoders☆46Mar 12, 2026Updated 2 months ago
- ☆27Oct 27, 2025Updated 7 months ago