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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 453
    Prev
    Next
    INDEX
    Explanations

    references to future trends and progressions

    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
    ��
    -0.76
    ilater
    -0.74
    ��
    -0.74
    notations
    -0.74
    swer
    -0.69
    anse
    -0.68
    kinson
    -0.68
    rf
    -0.67
    future
    -0.67
    antis
    -0.65
    POSITIVE LOGITS
     generation
    0.78
    Lv
    0.72
     stage
    0.62
     Zup
    0.61
     stages
    0.60
     installments
    0.59
    IRO
    0.59
     installment
    0.59
     manifestation
    0.59
     exaggeration
    0.59
    Activations Density 0.032%

    No Known Activations