Attention Gathers, MLPs Compose: A Causal Analysis of an Action-Outcome Circuit in VideoViT

📅 2026-03-11
📈 Citations: 0
Influential: 0
📄 PDF

career value

202K/year
🤖 AI Summary
Although trained solely on category labels, video classification models implicitly encode task-irrelevant yet semantically rich information about action outcomes—such as success or failure—posing challenges for trustworthy AI. This work employs mechanistic interpretability to perform causal reverse engineering on a pretrained VideoViT, revealing for the first time a distributed and redundant internal circuit dedicated to computing action outcomes. Specifically, attention heads aggregate low-level evidence while MLP blocks compose high-level concepts to construct success signals. The study identifies a progressively amplified semantic pathway spanning layers 5 to 11, confirming the complementary roles of attention and MLP components. Through activation patching and ablation experiments, the model demonstrates robust reliance on this implicit knowledge, highlighting its resilience and structured internal representation of outcome-related semantics.

Technology Category

Application Category

📝 Abstract
The paper explores how video models trained for classification tasks represent nuanced, hidden semantic information that may not affect the final outcome, a key challenge for Trustworthy AI models. Through Explainable and Interpretable AI methods, specifically mechanistic interpretability techniques, the internal circuit responsible for representing the action's outcome is reverse-engineered in a pre-trained video vision transformer, revealing that the "Success vs Failure" signal is computed through a distinct amplification cascade. While there are low-level differences observed from layer 0, the abstract and semantic representation of the outcome is progressively amplified from layers 5 through 11. Causal analysis, primarily using activation patching supported by ablation results, reveals a clear division of labor: Attention Heads act as "evidence gatherers", providing necessary low-level information for partial signal recovery, while MLP Blocks function as robust "concept composers", each of which is the primary driver to generate the "success" signal. This distributed and redundant circuit in the model's internals explains its resilience to simple ablations, demonstrating a core computational pattern for processing human-action outcomes. Crucially, the existence of this sophisticated circuit for representing complex outcomes, even within a model trained only for simple classification, highlights the potential for models to develop forms of 'hidden knowledge' beyond their explicit task, underscoring the need for mechanistic oversight for building genuinely Explainable and Trustworthy AI systems intended for deployment.
Problem

Research questions and friction points this paper is trying to address.

Trustworthy AI
hidden knowledge
action-outcome representation
video classification
Explainable AI
Innovation

Methods, ideas, or system contributions that make the work stand out.

mechanistic interpretability
activation patching
Video Vision Transformer
causal analysis
distributed circuit