© 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. 2439
    Prev
    Next
    INDEX
    Explanations

    ellipses or pauses in the text

    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
     namesake
    -0.62
     cousins
    -0.61
     quarry
    -0.55
     name
    -0.55
     qualitative
    -0.55
     Pegasus
    -0.54
     nephew
    -0.54
     cousin
    -0.53
     crem
    -0.53
     origins
    -0.53
    POSITIVE LOGITS
    ��
    0.90
    other
    0.87
    except
    0.82
    clear
    0.81
    ple
    0.81
    etheless
    0.75
    catch
    0.74
    OK
    0.72
     largeDownload
    0.72
    Interest
    0.71
    Activations Density 0.014%

    No Known Activations