Knowledge Base Regulation Tracker Standards & Frameworks OSS Directory AI Incident Database Research Paper Library Case Studies Society Articles News Jobs About Charter Sign inBecome a Member
Home/Research Paper Library/Zoom In

Zoom In

The manifesto for mechanistic interpretability, proposing features and circuits as the units of understanding networks.

circuitsmechanistic interpretabilitydistill

Research question

Can neural networks be understood as circuits of meaningful features?

Key findings

  • Proposes that features are fundamental units, connected by circuits, with universality across models - Documents curve detectors and other circuits in InceptionV1

Sources

PreviousDoes the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team PerformanceNextReliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks

Contribute

Spot an error, or know a record we should add? Members can propose additions and submit corrections.

Submit researchReport a correction or request removal

Related in Research Paper Library

X-SPUR: Explainable Surprisal-Based Protocol-Aware Unsupervised Reasoning for Automotive Ethernet Intrusion Detection

Automotive Ethernet carries heterogeneous multi-protocol traffic in modern in-vehicle networks, where labeled attack data are rarely available and the strongest prior unsupervised detector still relies on handcrafted…

Mechanistic interpretability2026

Delphi Scanner: efficient and interpretable static malware detection via API sequence modeling

Static malware detection for Windows Portable Executable files demands a careful balance between detection effectiveness, computational efficiency, and analytical interpretability. This paper introduces Delphi…

Mechanistic interpretability2026

Influence Score and Transformers interpretability: Measure of the Effective Impact of Attention Heads at inference time

We propose an influence score to quantify the contribution of attention heads to classification decisions in Transformer-based models designed for prompt injection detection. The score combines directional influence…

Mechanistic interpretability2026