© 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. 1743
    Prev
    Next
    INDEX
    Explanations

    phrases centered around themes of letting go and forgetting

    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
    fman
    -0.76
    zie
    -0.71
    ographer
    -0.71
    erman
    -0.67
    liest
    -0.66
    anship
    -0.66
    reenshot
    -0.65
    si
    -0.62
    gow
    -0.62
    nen
    -0.62
    POSITIVE LOGITS
     sentimental
    0.76
     obscurity
    0.73
     inco
    0.72
     sluggish
    0.71
     stale
    0.70
     junk
    0.70
     inertia
    0.70
     superficial
    0.69
     implicit
    0.69
    ARP
    0.68
    Activations Density 0.228%

    No Known Activations