Alternatives

Products that do what At 16K features, flat autoencoders break. Curved space doesn't does

High-Performance Hyperbolic Sparse Autoencoders for Mechanistic Interpretability - vishal-dehurdle/hypersae

1
HyperSAE – Sparse Autoencoders, reimagined in hyperbolic space▲6
High-Performance Hyperbolic Sparse Autoencoders for Mechanistic Interpretability - vishal-dehurdle/hypersae
18d ago · github.com
2L3
Llama 3.2 Interpretability with Sparse Autoencoders▲579
I spent a lot of time and money on this rather big side project of mine that attempts to replicate the mechanistic interpretability research on proprietary LLMs that was quite popular this year and produced great research papers by Anthropic [1], OpenAI [2] and Deepmind [3]. I am quite proud of this project and since I consider myself the target audience for HackerNews did I think that maybe some of you would appreciate this open research replication as well. Happy to answer any questions or face any feedback. Cheers [1]…
2024 · github.com
3L3
Llama 3.3 70B Sparse Autoencoders with API access▲201
2024 · goodfire.ai
4
DeepSeek-V3.2-Exp▲155
Long-context efficiency with DeepSeek Sparse Attention
Sep 2025
5TA
Thinc, a new deep learning library by the makers of spaCy and FastAPI▲250
2020 · thinc.ai
6WQ
Word2Bits – Quantized Word Vectors▲221
2018 · github.com
7ML
Model2vec – Lightning-fast Static Embeddings for RAG/Semantic Search▲28
We’ve recently open-sourced Model2vec, a method to distill sentence transformers into static embeddings that outperform all previous approaches by a large margin on MTEB. Our new models set a new state-of-the-art for static embeddings. Main features: - Our best model (potion-base-8M) has only 8M parameters, which is ~30mb on disk - Inference is ~500x faster than the distilled base model (bge-base), on a CPU - New models can be distilled in 30 seconds on a CPU without requiring a dataset - just a vocabulary - Numpy-only inference: The packaged can be install the package with minimal…
2024 · github.com
8WA
Wikipedia2Vec – A tool for learning embeddings of words and entities▲105
2018 · wikipedia2vec.github.io
9XF
Xcessiv – Fully managed web application for automated machine learning▲108
2017 · github.com
10HM
Hindley-Milner Type Inference Algorithm in OCaml▲136
2016 · github.com
11
Sonnet▲134
A new library for constructing neural networks from DeepMind
2017
12C0
Cherry2.0 – text classification without ML knowledge needed▲71
2019 · github.com
13
TensorFlow 1.0▲80
Open-source machine learning library by Google
2018
14AG
A general-purpose encoder-decoder framework for Tensorflow▲54
2017 · github.com
15WF
We fingerprinted 178 AI models' writing styles and similarity clusters▲78
We have a dataset of 3,095 standardized AI responses across 43 prompts. From each response, we extract a 32-dimension stylometric fingerprint (lexical richness, sentence structure, punctuation habits, formatting patterns, discourse markers). Some findings: - 9 clone clusters (>90% cosine similarity on z-normalized feature vectors) - Mistral Large 2 and Large 3 2512 score 84.8% on a composite metric combining 5 independent signals - Gemini 2.5 Flash Lite writes 78% like Claude 3 Opus. Costs 185x less - Meta has the strongest provider "house style" (37.5x distinctiveness ratio) - "Satirical…
Apr 2026 · rival.tips
16AE
An encoding/decoding tool for Martin David's theoretical S language▲24
2016 · ramadis.github.com
17I4
Ideogram 4.0 – open-weight 9.3B text-to-image model▲46
It's our new text-to-image model: a 9.3B single-stream diffusion transformer trained entirely from scratch. We focused heavily on controllability through structured JSON prompts, with strong text rendering, spatial awareness through bounding box guidance, and color palette control. It has the best text rendering of any open-weight model we've tested so far, and the NF4 quantized checkpoint runs on a single 24GB GPU. For more technical details and examples see our blog post: https://ideogram.ai/blog/ideogram-4.0/ We will be happy to answer any questions :)
Jun 2026 · github.com
18IB
I built a full mulimodal LLM by merging multiple models into one▲40
2025 · github.com
19HA
_hyperscript – an async-transparent scripting langauge for the web▲11
2021 · hyperscript.org
20WC
We cut RAG latency ~2× by switching embedding model▲27
Nov 2025 · myclone.is
21IM
I made a 3D visual "thesaurus" for English▲19
Just a fun toy I wanted to make. I've been studying and playing around with language models lately and have always been intrigued by how words are processed by these models. Since the vectors generated by embedding models is in very high dimensional space, I thought it would be cool to reduce them to 3D vectors and visualise them myself. This is what I have so far!
2023 · seesaurus.com
22LA
Lark, a modern parsing library with Earley and LALR(1) implementations▲15
2017 · github.com
23UV
UForm v2 – tiny CLIP-like embeddings in 21 languages and Graphcore API▲16
I want to share the most recent model release we have prepared. It's a Vision-Language understanding Transformer. It has 40% fewer parameters than vanilla CLIP while performing much better on text-to-image retrieval, where it's also beneficial that our output embeddings have 2x fewer dimensions (256 vs. 512). Moreover, it supports 21 languages, including popular English, Hindi, Chinese, Arabic, and lower-resource languages like Ukrainian, Hebrew, and Armenian. We have packed the library into ONNX and CoreML, providing PyTorch inference code for CPUs and GPUs and PopTorch code for Graphcore…
2023 · github.com
24K2
KTransformers–236B Model and 1M Context LLM Inference on Local Machines▲20
Hey Hacker News! We are excited to share our open-source project, KTransformers, a flexible framework designed for cutting-edge LLM inference optimizations! Leveraging state-of-the-art kernels from llamafile and marlin, KTransformers seamlessly enhances the performance of HuggingFace Transformers, making it possible to operate large 236B MoE models or extremely long 1M context locally with promising speed. KTransformers is a Python-centric framework designed with extensibility at its core. By implementing and injecting an optimized module with a single line of code, users gain access to a…
2024 · github.com

Ranked by how close each launch is in meaning, then by votes. Refine with a description →