Open Issues Need Help
View All on GitHub AI/ML • Transformer Optimization
[Possible Bug] Running multiple initialization seeds 2 months ago
AI Summary: Debug a KeyError in a Python library for training sparse autoencoders. The error occurs when attempting to train with multiple initialization seeds, stemming from a potential mismatch in how SAE names are handled during initialization and model forward passes. The solution likely involves correcting the naming convention for SAEs when multiple seeds are used, ensuring consistency between the `saes` dictionary keys and the hookpoint names used during the model's forward pass.
Complexity:
4/5
bug good first issue