I read TurnTrout’s summary, of this plan, so this may be entirely unrelated, but the recent paper Generalizing Backpropagation for Gradient-Based Interpretability (video) seems like a good tool for this brand of interpretability work. May want to reach out to the authors to prove the viability of your paradigm and their methods, or just use their methods directly.
I read TurnTrout’s summary, of this plan, so this may be entirely unrelated, but the recent paper Generalizing Backpropagation for Gradient-Based Interpretability (video) seems like a good tool for this brand of interpretability work. May want to reach out to the authors to prove the viability of your paradigm and their methods, or just use their methods directly.