Understanding the flow of information in Deep Neural Networks (DNNs) is a\nchallenging problem that has gain increasing attention over the last few years.\nWhile several methods have been proposed to explain network predictions, there\nhave been only a few attempts to compare them from a theoretical perspective.\nWhat is more, no exhaustive empirical comparison has been performed in the\npast. In this work, we analyze four gradient-based attribution methods and\nformally prove conditions of equivalence and approximation between them. By\nreformulating two of these methods, we construct a unified framework which\nenables a direct comparison, as well as an easier implementation. Finally, we\npropose a novel evaluation metric, called Sensitivity-n and test the\ngradient-based attribution methods alongside with a simple perturbation-based\nattribution method on several datasets in the domains of image and text\nclassification, using various network architectures.\n