SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training
SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training explores SAE-based Transferability Score predicts LLM transferability across domains without fine-tuning.. Commercial viability score: 5/10 in LLM Evaluation.
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 ThisSparse Visual Thought Circuits in Vision-Language ModelsViability: 4.0
- Builds On ThisSynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic DataViability: 4.0
- Prior WorkSparse Autoencoders Reveal Interpretable and Steerable Features in VLA ModelsViability: 5.0
- Prior WorkDLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse AutoencodersViability: 5.0
- Prior WorkLarge Reasoning Models Struggle to Transfer Parametric Knowledge Across Scripts