Alright so we have: - Bayesian Influence Functions allow us to find a training data:output loss correspondence- Maybe the eigenvalues of the eNTK (very similar to influence function) corresponds to features in the data- Maybe the features in the dataset can be found with an SAETherefore (will test this later today) maybe we can use SAE features to predict the influence function.
Alright so we have:
- Bayesian Influence Functions allow us to find a training data:output loss correspondence
- Maybe the eigenvalues of the eNTK (very similar to influence function) corresponds to features in the data
- Maybe the features in the dataset can be found with an SAE
Therefore (will test this later today) maybe we can use SAE features to predict the influence function.