paper-with-me

홈 › Papers

Mechanistic Interpretability of Fine-Tuned Vision Transformers on Distorted Images: Decoding Attention Head Behavior for Transparent and Trustworthy AI

2025-03-24 · Nooshin Bahador

Mechanistic interpretability improves the safety, reliability, and robustness of large AI models. This study examined individual attention heads in vision transformers (ViTs) fine tuned on distorted 2D spectrogram images containing non relevant content (axis labels, titles, color bars). By introducing extraneous features, the study analyzed how transformer components processed unrelated information, using mechanistic interpretability to debug issues and reveal insights into transformer architectures. Attention maps assessed head contributions across layers. Heads in early layers (1 to 3) showed minimal task impact with ablation increased MSE loss slightly ({\mu}=0.11%, {\sigma}=0.09%), indicating focus on less critical low level features. In contrast, deeper heads (e.g., layer 6) caused a threefold higher loss increase ({\mu}=0.34%, {\sigma}=0.02%), demonstrating greater task importance. Intermediate layers (6 to 11) exhibited monosemantic behavior, attending exclusively to chirp regions. Some early heads (1 to 4) were monosemantic but non task relevant (e.g. text detectors, edge or corner detectors). Attention maps distinguished monosemantic heads (precise chirp localization) from polysemantic heads (multiple irrelevant regions). These findings revealed functional specialization in ViTs, showing how heads processed relevant vs. extraneous information. By decomposing transformers into interpretable components, this work enhanced model understanding, identified vulnerabilities, and advanced safer, more transparent AI.

📄 PDF Abstract BibTeX arXiv:2503.18762

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
NON 설명 없음
Focus 설명 없음

Similar Papers 제목 키워드 기반

Seeing Through Circuits: Faithful Mechanistic Interpretability for Vision Transformers

2026-04-15 · Nina Żukowska, Wolfgang Stammer, Bernt Schiele, Jonas Fischer arxiv

Transparency of neural networks' internal reasoning is at the heart of interpretability research, adding to trust, safety, and understanding of these models. The field of mechanistic interpretability has recently focused…

Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video

2025-04-28 · Sonia Joseph, Praneet Suresh, Lorenz Hufe, Edward Stevinson 외

Robust tooling and publicly available pre-trained models have helped drive recent advances in mechanistic interpretability for language models. However, similar progress in vision mechanistic interpretability has been hi…

Interpreting Affine Recurrence Learning in GPT-style Transformers

2024-10-22 · Samarth Bhargav, Alexander Gu

Understanding the internal mechanisms of GPT-style transformers, particularly their capacity to perform in-context learning (ICL), is critical for advancing AI alignment and interpretability. In-context learning allows t…

In-Context Learning

Extracting Finite State Machines from Transformers

2024-10-08 · Rik Adriaensen, Jaron Maene

Fueled by the popularity of the transformer architecture in deep learning, several works have investigated what formal languages a transformer can learn. Nonetheless, existing results remain hard to compare and a fine-gr…

LLM-Powered Flood Depth Estimation from Social Media Imagery: A Vision-Language Model Framework with Mechanistic Interpretability for Transportation Resilience

2026-03-17 · Nafis Fuad, Xiaodong Qian arxiv

Urban flooding poses an escalating threat to transportation network continuity, yet no operational system currently provides real-time, street-level flood depth information at the centimeter resolution required for dynam…

Depth Estimation