Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation
Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation explores This research investigates why sparse autoencoders fail at compositional generalization, identifying dictionary learning as the core challenge for scalable sparse inference.. Commercial viability score: 3/10 in LLM 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 $10K - $14K 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 ThisOne Language, Two Scripts: Probing Script-Invariance in LLM Concept RepresentationsViability: 2.0
- Builds On ThisDo Language Models Encode Semantic Relations? Probing and Sparse Feature AnalysisViability: 2.0
- Builds On ThisInformation Routing in Atomistic Foundation Models: How Equivariance Creates Linearly Disentangled RepresentationsViability: 1.0
- Higher ViabilitySparse Visual Thought Circuits in Vision-Language ModelsViability: 4.0
- Higher ViabilityFrom Atoms to Trees: Building a Structured Feature Forest with Hierarchical Sparse Autoencoders