
tuned-lens
by AlignmentResearch (organization)
Tools for understanding how transformer predictions are built layer-by-layer (description from the project’s GitHub page)
Repository facts
- Stars
- 619
- Forks
- 77
- Open issues and pull requests
- 25
- Primary language
- Python
- License
- MIT License (MIT)
- Owner
- AlignmentResearch · Organization
- Created
- Oct 3, 2022
- Last push
- Aug 7, 2025
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 443: arc53/DocsGPT
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
18,322 starsPythonMITLast push Oct 18, 2026
Rank 851: xorbitsai/inference
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unif…
9,616 starsPythonApache-2.0Last push Oct 18, 2026
Rank 890: MakazhanAlpamys/Soup
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
9,314 starsPythonApache-2.0Last push Oct 18, 2026
Rank 998: jessevig/bertviz
BertViz: Visualize Attention in Transformer Models
8,200 starsPythonApache-2.0Last push Jan 8, 2026
Rank 1,857: SwanHubX/SwanLab
⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / verl / LLaMA Fact…
4,304 starsPythonApache-2.0Last push Oct 15, 2026
Rank 2,753: linto-ai/whisper-timestamped
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
2,855 starsPythonAGPL-3.0Last push Sep 28, 2026