Towards Explainability of SLMs by investigating Token Level Activation

• URL: http://arxiv.org/abs/2605.22377v1
• Date: Thu, 21 May 2026 12:09:12 GMT
• Title: Towards Explainability of SLMs by investigating Token Level Activation
• Abstract summary: This work introduces a framework for quantifying token-level representational importance using hidden-state activation strengths at Layer 8 of BERT.<n>The proposed Activation Flow Network (AFN) framework computes Token Activation Strength using the L2 norm of Layer-8 hidden representations.<n>The study further introduces a threshold-based activation bucket formulation that partitions tokens into HIGH-activation and LOW-activation groups.
• Score: 2.7590644934977764
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 introduces a lightweight and model-agnostic framework for quantifying token-level representational importance using hidden-state activation strengths at Layer 8 of BERT. The proposed Activation Flow Network (AFN) framework computes Token Activation Strength using the L2 norm of Layer-8 hidden representations, enabling direct ranking of semantically salient tokens. The study further introduces a threshold-based activation bucket formulation that partitions tokens into HIGH-activation and LOW-activation groups using an empirical upper-quartile activation boundary. Experimental observations demonstrate that semantically meaningful content words consistently occupy the HIGH-activation bucket and dominate representational activation shifts, while structurally supportive tokens contribute comparatively less. The results suggest that Layer 8 acts as a critical semantic consolidation zone balancing structural and semantic information processing. By revealing how activation magnitudes concentrate around semantically informative tokens, this work provides an interpretable and computationally efficient alternative to attentioncentric analysis, contributing toward transforming BERT from a "black box" into a more transparent "glass box" model for natural language understanding.

Related papers

• ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both [55.182037225013836]
  ATLAS is a framework in which a single discrete 'word', termed as a functional token, serves both as an agentic operation and a latent visual reasoning unit.<n> ATLAS achieves superior performance on challenging benchmarks while maintaining clear interpretability.
  arXiv  Detail & Related papers  (2026-05-14T17:59:55Z)
• Beyond Attention Magnitude: Leveraging Inter-layer Rank Consistency for Efficient Vision-Language-Action Models [75.27089289058613]
  We introduce textbfTIES (textbfTau-guided textbfInter-layer textbfEfficient textbfSelection), a dynamic framework guided by inter-layer token ranking consistency.<n>On the CogACT + SIMPLER benchmark, TIES improves average success rates by 6% while reducing token usage by 78%, and demonstrate strong generalization across diverse decoders and benchmarks.
  arXiv  Detail & Related papers  (2026-03-26T02:13:03Z)
• Enhancing Hyperspace Analogue to Language (HAL) Representations via Attention-Based Pooling for Text Classification [0.0]
  We develop a learnable, temperature-scaled additive attention mechanism into the HAL representation pipeline.<n>We evaluate the proposed architecture on the IMDB sentiment analysis dataset.
  arXiv  Detail & Related papers  (2026-03-20T17:25:09Z)
• Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMs [27.02559478797257]
  We study attention sinks and massive activations in large language models (LLMs)<n>We introduce a simple decorrelation loss that reduces cosine similarity between BOS and other tokens, effectively mitigating intermediate sinks and massive activations.<n>Our method improves word error rate (WER) under high audio-visual feature downsampling while remaining stable at lower downsampling rates.
  arXiv  Detail & Related papers  (2025-10-26T09:44:20Z)
• Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization [56.083511902353365]
  Reinforcement learning (RL) typically applies uniform credit across an entire generation of Large language models.<n>This work positions attention as a privileged substrate that renders the internal logic of LLMs as a mechanistic blueprint of reasoning itself.<n>We introduce three novel RL strategies that dynamically perform targeted credit assignment to critical nodes.
  arXiv  Detail & Related papers  (2025-10-15T13:49:51Z)
• Explaining multimodal LLMs via intra-modal token interactions [55.27436637894534]
  Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood.<n>We propose enhancing interpretability by leveraging intra-modal interaction.
  arXiv  Detail & Related papers  (2025-09-26T14:39:13Z)
• ATAS: Any-to-Any Self-Distillation for Enhanced Open-Vocabulary Dense Prediction [7.353998772647553]
  Any-to-Any Self-Distillation (ATAS) is a novel approach that simultaneously enhances semantic coherence and fine-grained alignment.<n>ATAS achieves substantial performance gains on open-vocabulary object detection and semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2025-06-10T10:40:10Z)
• Abstract Counterfactuals for Language Model Agents [3.7540612510652176]
  Abstract Counterfactuals is a framework that emphasises high-level characteristics of actions and interactions within an environment.<n>We conduct experiments on text-based games and counterfactual text generation, while considering both token-level and latent-space interventions.
  arXiv  Detail & Related papers  (2025-06-03T14:44:26Z)
• "Principal Components" Enable A New Language of Images [79.45806370905775]
  We introduce a novel visual tokenization framework that embeds a provable PCA-like structure into the latent token space.<n>Our approach achieves state-of-the-art reconstruction performance and enables better interpretability to align with the human vision system.
  arXiv  Detail & Related papers  (2025-03-11T17:59:41Z)
• Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens [57.37893387775829]
  We introduce a fast and balanced clustering method, named Semantic Equitable Clustering (SEC)<n>SEC clusters tokens based on their global semantic relevance in an efficient, straightforward manner.<n>We propose a versatile vision backbone, SECViT, to serve as a vision language connector.
  arXiv  Detail & Related papers  (2024-05-22T04:49:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.