A Mechanistic Study of AI-Text Detection Neurons in Frozen BERT: Sparse Probing and Activation Patching on RAID

arXiv:2609.30287 · cs.CL, cs.AI · Submitted 2026-09-08 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-08

Updated: 2026-09-08

Terminology

• Accuracy — 38× in this paper · explained in 1 episode
• AUC — 26× in this paper · explained in 2 episodes
• Ablation — 26× in this paper · explained in 1 episode
• Activation Patching — 17× in this paper · explained in 2 episodes
• Transformer — 13× in this paper · explained in 2 episodes
• Benchmark — 9× in this paper · explained in 2 episodes
• Interpretability — 9× in this paper · explained in 15 episodes
• Core — 4× in this paper · explained in 2 episodes
• Redundancy — 4× in this paper · explained in 2 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Parsimony — 3× in this paper · explained in 2 episodes
• Linear probe — 2× in this paper · explained in 2 episodes
• Adversarial Activation Patching — 1× in this paper · explained in 1 episode
• Adversarial Robustness — 1× in this paper · explained in 3 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Transformer Models — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Atomic Literary Styling: Mechanistic Manipulation of Prose Generation in Neural Language Models
• How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection
• How to use and interpret activation patching
• Mistral 7B
• RoBERTa: A Robustly Optimized BERT Pretraining Approach
• GPT-4 Technical Report
• Why AI-Generated Text Detection Fails: Evidence from Explainable AI Beyond Benchmark Accuracy
• Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers
• Release Strategies and the Social Impacts of Language Models
• Llama 2: Open Foundation and Fine-Tuned Chat Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering