The experimental results of LEAP (Liquefaction Experiments and Analysis Projects) centrifuge test replicas of a saturated sloping deposit are used to assess the sensitivity of soil accelerations to variability in input motion and soil deposition. A difference metric is used to quantify the dissimilarities between recorded acceleration time histories. This metric is uniquely decomposed in terms of four difference component measures associated with phase, frequency shift, amplitude at 1 Hz, and amplitude of frequency components higher than 2 Hz (2 + Hz). The sensitivity of the deposit response accelerations to differences in input motion amplitude at 1 Hz and 2 + Hz and cone penetration resistance (used as a measure reflecting soil deposition and initial grain packing condition) was obtained using a Gaussian process-based kriging. These accelerations were found to be more sensitive to variations in cone penetration resistance values than to the amplitude of the input motion 1 Hz and 2 + Hz (frequency) components. The sensitivity functions associated with this resistance parameter were found to be substantially nonlinear.