Conceptgradient decomposition
Gradient Decomposition
A method that decomposes the gap between linear probe predictions and true intervention attribution into several analyzable terms, showing that intervention attribution can be estimated via gradients.
Timeline (last 90 days)
Oct 14
The gradient decomposition given in the paper breaks down the gap between linear probe predictions and true intervention attribution, showing that intervention attribution can be estimated via gradients.
Unverified50%