© 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. 1226
    Prev
    Next
    INDEX
    Explanations

    instances of the interstate highway system

    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
    ella
    -0.84
    ese
    -0.71
    wcsstore
    -0.70
    ansom
    -0.69
    stall
    -0.68
    nir
    -0.66
    icken
    -0.66
    rero
    -0.66
    oma
    -0.65
    sworth
    -0.65
    POSITIVE LOGITS
    Balance
    0.81
    spect
    0.65
    ��
    0.62
    NUM
    0.62
    hibit
    0.62
    Relations
    0.60
    dinand
    0.58
    formation
    0.58
    Team
    0.58
    Switch
    0.58
    Activations Density 0.016%

    No Known Activations