Close Menu
techwavedispatch.com

    Subscribe to Updates

    Get the latest creative news from FooBar about art, design and business.

    What's Hot

    [2609.04910] Fast Gauss Sums via Flash Attention

    November 21, 2026

    17 Best Gifts for Women in the Enshittocene (2026)

    November 21, 2026

    Disentangling Monitor Hardware Artifacts and Smoothing Lag for Shift-Robust Intraoperative EEG and Hemodynamic Risk Calibration

    November 21, 2026
    Facebook X (Twitter) Instagram
    Trending
    • [2609.04910] Fast Gauss Sums via Flash Attention
    • 17 Best Gifts for Women in the Enshittocene (2026)
    • Disentangling Monitor Hardware Artifacts and Smoothing Lag for Shift-Robust Intraoperative EEG and Hemodynamic Risk Calibration
    • Learning Feature-Specific Timescales in Language Model Representations
    • Goal-Guided Reinforcement Learning via Fine-Tuning Vision-Language Models
    • [2606.16694] When Does Depth Matter For In-Context Learning? Adaptive Inference in Deep Transformers
    • Bytedance argues most AI training phases are unnecessary and backs it up with a competitive open model
    • PosteriorBench: Evaluating Behavior Posterior Sampling in Language Models
    Facebook X (Twitter) Instagram
    techwavedispatch.com
    Subscribe
    Saturday, November 21
    • Home
    • AI Tools & Software
    • Machine Learning
    • Generative AI
    • Robotics & Automation
    • Future Tech & Hardware
    • AI in Business
    • Ethics & Regulations
    • More
      • Gadgets & Smart Devices
      • Cybersecurity & AI
      • Tech Breakthroughs
    techwavedispatch.com
    Home»Machine Learning»Non-Gaussianity Reveals Interpretable Directions in Language Models
    Machine Learning

    Non-Gaussianity Reveals Interpretable Directions in Language Models

    adminBy adminNovember 18, 2026No Comments2 Mins Read
    Facebook Twitter Pinterest LinkedIn Tumblr Email
    Non-Gaussianity Reveals Interpretable Directions in Language Models
    Share
    Facebook Twitter LinkedIn Pinterest Email

    [Submitted on 10 Jun 2026 (v1), last revised 17 Nov 2026 (this version, v3)]

    View a PDF of the paper titled ICA Lens: Non-Gaussianity Reveals Interpretable Directions in Language Models, by Sida Liu and 3 other authors

    View PDF
    HTML (experimental)

    Abstract:Finding human-interpretable directions in language-model activations is important for understanding and controlling model behavior. These directions are usually discovered through indirect learning objectives such as sparse reconstruction, but it remains unclear what existing statistical structure distinguishes interpretable directions and whether that structure can be used directly for feature discovery. We find that non-Gaussianity provides such a signature: projection distributions of natural-text residual-stream activations along sparse autoencoder (SAE) decoder directions are substantially more non-Gaussian than those along random directions, with most contexts forming a concentrated background and recurring patterns often occupying one tail. This raises a natural question: if interpretable directions tend to have non-Gaussian projection distributions, can we discover them by searching for non-Gaussian directions directly in activation space, without training another sparse dictionary? To test this hypothesis, we introduce ICA Lens, a practical workflow for efficient discovery, reliable annotation, and faithful evaluation of non-Gaussian directions in LLM residual-stream activations. Across GPT-2 Small, Gemma 2 2B, and Qwen 3.5 9B Base, we find that (1) the recovered non-Gaussian directions capture coherent lexical, syntactic, and semantic patterns under both human and LLM-based evaluation; (2) non-Gaussianity is positively associated with both human-label confidence and automated interpretability; and (3) the resulting coordinates are competitive with SAEs across interpretability, sparse reconstruction, concept prediction, and causal interventions, while fitting in minutes per layer and using 7-43 times less memory. These results show that non-Gaussianity is a direct unsupervised signal for discovering interpretable and useful structure in activations.

    Submission history

    From: Feijiang Han [view email]
    [v1]
    Wed, 10 Jun 2026 06:53:58 UTC (2,296 KB)
    [v2]
    Mon, 19 Oct 2026 17:23:26 UTC (6,395 KB)
    [v3]
    Tue, 17 Nov 2026 04:23:38 UTC (7,693 KB)

    Directions Interpretable Language Models NonGaussianity Reveals
    Share. Facebook Twitter Pinterest LinkedIn Tumblr Email
    admin
    • Website

    Related Posts

    [2609.04910] Fast Gauss Sums via Flash Attention

    November 21, 2026

    Disentangling Monitor Hardware Artifacts and Smoothing Lag for Shift-Robust Intraoperative EEG and Hemodynamic Risk Calibration

    November 21, 2026

    Learning Feature-Specific Timescales in Language Model Representations

    November 21, 2026
    Leave A Reply Cancel Reply

    Top Posts

    NVIDIA Is Investigating Reports That CEO Jensen Huang Was The Target Of Chinese Spy Efforts

    November 8, 202619 Views

    ADIndex: Layer-Adaptive Sparse Attention Indexing via Group-Level Distillation

    November 11, 20265 Views

    Anthropic releases new Mythos and Fable models amid RSI concerns

    November 9, 20265 Views

    If AGI is so close, why is everyone leaving? The neolabs and their bets

    November 6, 20265 Views
    Don't Miss
    Machine Learning

    [2609.04910] Fast Gauss Sums via Flash Attention

    By adminNovember 21, 20260

    [Submitted on 4 Sep 2026 (v1), last revised 19 Nov 2026 (this version, v2)] View…

    17 Best Gifts for Women in the Enshittocene (2026)

    November 21, 2026

    Disentangling Monitor Hardware Artifacts and Smoothing Lag for Shift-Robust Intraoperative EEG and Hemodynamic Risk Calibration

    November 21, 2026

    Learning Feature-Specific Timescales in Language Model Representations

    November 21, 2026
    About Us

    Welcome to TechWave Dispatch

    At TechWave Dispatch, we bring you the latest news, insights, and developments from the ever-evolving world of technology. Our mission is to keep readers informed about the innovations shaping our digital future.

    From artificial intelligence and machine learning to cybersecurity, robotics, smart devices, and groundbreaking technologies, we cover the topics that matter in today's fast-moving tech landscape.

    Our Picks

    [2609.04910] Fast Gauss Sums via Flash Attention

    November 21, 2026

    17 Best Gifts for Women in the Enshittocene (2026)

    November 21, 2026

    Disentangling Monitor Hardware Artifacts and Smoothing Lag for Shift-Robust Intraoperative EEG and Hemodynamic Risk Calibration

    November 21, 2026
    Most Popular

    After blocking Muse, Amazon now lets users text Alexa to help them shop

    November 6, 20260 Views

    A controlled world for robot learning and evaluation

    November 6, 20260 Views

    Egyptian and Nigerian English join the Open ASR Leaderboard

    November 6, 20260 Views
    Facebook X (Twitter) Instagram Pinterest
    • Terms and Conditions
    • Privacy Policy
    • Contact Us
    • About Us
    © 2026 TechWave Dispatch. All Rights Reserved.

    Type above and press Enter to search. Press Esc to cancel.