AI RESEARCH
Towards Explainability of SLMs by investigating Token Level Activation
arXiv CS.LG
•
ArXi:2605.22377v1 Announce Type: new Transformer-based language models such as BERT having 110M+ parameters have revolutionized natural language understanding, yet their internal mechanisms remain largely opaque to researchers and practitioners. Traditional attention-based interpretability methods often emphasize structurally important but semantically weak tokens such as punctuation marks rather than meaningful semantic relationships. This work