Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mkurman/captum
Captum (PyTorch) — model interpretability and feature attribution. Integrated Gradients, DeepLIFT, SmoothGrad, Occlusion, SHAP approximation, and Layer-wise Relevance Propagation. For vision and text models.
Passed 18 of 22 test cases with the skill, and 16 of 22 without it.
2 fixed16 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
What is the official documentation website URL for Captum?
| Checked | Without skill | With skill |
|---|---|---|
| The response includes the URL https://captum.ai/docs/. | Missed | Passed |
The instructions your model reads when the skill loads.
Captum (Comprehension in PyTorch) provides model interpretability for PyTorch models. Implements Integrated Gradients, Gradient SHAP, DeepLIFT, Occlusion, Feature Ablation, and Layer Conductance. Supports computer vision, NLP, and tabular models.
uv pip install captum
import torch
import torch.nn as nn
from captum.attr import IntegratedGradients
model = nn.Linear(10, 2)
input = torch.randn(1, 10)
baseline = torch.zeros(1, 10)
ig = IntegratedGradients(model)
attrs = ig.attribute(input, baseline, target=0)
print(f"Feature attributions: {attrs}")
from captum.attr import Occlusion
occ = Occlusion(model)
attrs = occ.attribute(input, target=0, sliding_window_shapes=(1,)) # 1D
print(attrs)
from captum.attr import visualization as viz
test cases passed, vs 16 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.