arXiv (All)
open access
MechaTerp-TRACE: A Novel Approach for Component Ablation Analysis in Language Models
Interpretability research on large language models has produced accounts of factual recall in feed-forward layers and of token relationships in self-attention, but little work offers a unified way to compare the causal contribution of different architecture components to a model's output. We introdu
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Towards Intrinsic Interpretability of Large Language Models:A Survey of Design Principles and Architectures#31283
- The Misery of Mechanistic Interpretability: A Formal Perspective#1109531
- When Do Attention-Head Ablations Support Causal Claims? Projection-Level Confounds, Floor Effects, and Matched Controls#1155308
- ReBeCA: Unveiling Interpretable Behavior Hierarchy behind the Iterative Self-Reflection of Language Models with Causal Analysis#974322
- Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs#1141599
Record · ID 1036846
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive