ML Application · Python
silico-e4b-sae-run
What it is
The repository trains a 42-layer JumpReLU Sparse Autoencoder (SAE) atlas for the Gemma 4 E4B language model using the E2B recipe and an event-aware trainer with automatic sparsity control. It generates a private Hugging Face dataset containing the SAEs and includes scripts for training, verification, and result aggregation.
Where it counts
- Machine Learning80%
- NLP & LLMs80%
- MLOps30%
- Data Science20%
How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.
Around it on the Machine Learning board
Whole board- 09, shared rankmamba-viewAI Developer Tool · Python62.2AdvancedRickMachine Learning
- 09, shared rankResNet_Family-from-scratchArchitecture Reimplementation · Jupyter Notebook62.2AdvancedPop AlexandruMachine Learning
- 11, shared rankvid-factoryML Application · JavaScript62.0AdvancedJarad PeckenpaughMachine Learning
- 11, shared ranksilico-e4b-sae-runML Application · Python62.0AdvancedRickMachine Learning
- 13mamba3-atlas-imageAI Developer Tool · Python61.5AdvancedRickMachine Learning