The relprop method of the Linear layer

[Hongbo-Z]

HI Chefer,

Is there a typo with Lines 218 to 219

Transformer-Explainability/modules/layers_ours.py

Lines 218 to 219 in c3e578f

	S1 = safe_divide(R, Z1 + Z2)
	S2 = safe_divide(R, Z1 + Z2)

which should be the below?
S1 = safe_divide(R, Z1)
S2 = safe_divide(R, Z2)
according to https://github.com/wjNam/Relative_Attributing_Propagation/blob/7fa96822740591b605712f251e556ec8487d1eea/modules/layers.py#L268-L269C36

Thanks,

Hongbo

[michaelkiper]

I want to follow this issue as well. It's something I noticed as well. Curious why you add by both the Z1 and Z2 terms to project the Relevance