Causal Interpretation of Neural Network Computations with Contribution Decomposition
Causal Interpretation of Neural Network Computations with Contribution Decomposition explores CODEC decomposes neural network behavior into sparse motifs of hidden-neuron contributions, enabling causal manipulations and human-interpretable visualizations.. Commercial viability score: 7/10 in Neural Network Interpretability.
BUILDER'S SANDBOX
Build This Paper
Use an AI coding agent to implement this research.
OpenAI CodexAI Agent
Lightweight coding agent in your terminal.
Claude CodeAI Agent
Agentic coding tool for terminal workflows.
AntiGravity IDEScaffolding
AI agent mindset installer and workflow scaffolder.
CursorIDE
AI-first code editor built on VS Code.
VS CodeIDE
Free, open-source editor by Microsoft.
Recommended Stack
Startup Essentials
Estimated $9K - $13K over 6-10 weeks.
See exactly what it costs to build this -- with 3 comparable funded startups.
7-day free trial. Cancel anytime.
Discover the researchers behind this paper and find similar experts.
7-day free trial. Cancel anytime.
Related Papers
- Builds On ThisWhat is Missing? Explaining Neurons Activated by Absent ConceptsViability: 2.0
- Builds On ThisStop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional GeneralisationViability: 3.0
- Builds On ThisLanguage Model Circuits Are Sparse in the Neuron BasisViability: 5.0
- Builds On ThisPost-hoc Self-explanation of CNNsViability: 4.0
- Builds On ThisStructural Compositional Function Networks: Interpretable Functional Compositions for Tabular Discovery