Gabriele Sarti

A possible visualization of saliency not relying on the entire matrix visualization might use either [Ecco.js](https://github.com/jalammar/ecco/blob/0ef61c51b76c48cd8c21c7807c20510565f307de/src/ecco/output.py#L204) or [gradio.HighlightedText](https://huggingface.co/spaces/joaogante/color-coded-text-generation)

Hi @MoritzLaurer , thanks for your comment! The slowness you report is most likely specific to the `discretized_integrated_gradient` method, since the current implementation builds non-linear interpolation paths in a sequential...

Current status: - DIG attribution was made compatible with newer changes (decoder-only model support, etc.) and supports both source and source-target attribution. - The problematic behavior of inconsistent outputs when...

Hi @soumyasanyal, FYI our library supports your method Discretized IG for feature attribution, but at the moment we are experiencing some issues with consistency across single-example and batched attribution (i.e....

I wouldn't dismiss the last errors (with `PYTORCH_ENABLE_MPS_FALLBACK=1`) as MPS problems necessarily, since they do not seem to be related to the content of the computed matrices, but rather to...

Thanks for testing this @lsickert! Maybe worth raising an issue on HF transformers to understand where's the issue since it's clearly a problem with generation. Would you be willing to...