Repository profile
A library for mechanistic interpretability of GPT-style language models
Repository updates
Get generated TransformerLensOrg/TransformerLens development summaries by email, or follow the weekly and monthly RSS feeds.
Sign in to subscribe by email. RSS feeds are public.
Sign in to subscribeTracked growth, recent movement, and commit velocity from stored repository snapshots.
Latest capture 2026-07-16 03:06
5 captures since 2026-05-25
Stars from baseline +217
All tracked data
Frameworks, package managers, ecosystems, and dependency manifests found during catalog scans.
Scanned 2026-07-16 03:06
pyproject.toml
python ecosystem,
60 dependencies
uv.lock
python ecosystem,
0 dependencies
Searchable topics, generated tags, and stack labels that explain where this repository fits.
Agent instructions and tool configuration paths found in the repository tree.
AI agent config detected
Key config paths
5 more config paths detected.
Nearest indexed repositories by embedding similarity.
Training Sparse Autoencoders on Language Models
State-of-the-Art Embeddings, Retrieval, and Reranking
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Ongoing research training transformer models at scale
Mamba SSM architecture
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
