© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 11292
    Prev
    Next
    INDEX
    Explanations

    names and concepts related to the name "Kenny"

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly those that start with "Kenny" or "Penny."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icity
    -0.97
    itri
    -0.97
    ifying
    -0.89
    ising
    -0.87
    izations
    -0.83
    inen
    -0.82
    ified
    -0.81
    ic
    -0.79
    atform
    -0.79
    andowski
    -0.78
    POSITIVE LOGITS
    pole
    0.87
     Arcade
    0.80
    stick
    0.76
     dreadful
    0.75
     Niet
    0.72
     Goodman
    0.71
     Ches
    0.70
     Kong
    0.70
     Sparrow
    0.69
    Bee
    0.69
    Activations Density 0.090%

    No Known Activations