Work Done
- Loaded in EMNIST dataset and ran an SAE + meta-sae on it.
Confusions
- how do I measure the impact of continuous meta-saes?
- run MNIST dataset and see if there are more distinct pattenrs that emerge over time
Next Steps
- Graph the activation distribution for the sae vs the meta-sae
- this claude chat has some of the code
- Look at the work of the meta-sae paper
- distill it down into notes and replicate its experiments
- Deploy the site at some point