© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2074
    Prev
    Next
    INDEX
    Explanations

    phrases indicating projections or estimates tied to specific time frames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.73
    pc
    -0.69
     detrim
    -0.68
    hin
    -0.65
    erie
    -0.64
    MpServer
    -0.62
    haven
    -0.62
    igi
    -0.62
     largeDownload
    -0.62
     artif
    -0.62
    POSITIVE LOGITS
     2019
    1.09
     2020
    1.06
     2021
    0.99
     2025
    0.90
     2030
    0.87
     2018
    0.85
    redo
    0.85
     2022
    0.84
     2024
    0.83
     2014
    0.83
    Activations Density 0.032%

    No Known Activations