© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 2288
    Prev
    Next
    INDEX
    Explanations

    references to the name "Kate" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Kate."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atio
    -0.80
    ATIONS
    -0.74
     externalToEVAOnly
    -0.69
    ATIVE
    -0.69
    Interstitial
    -0.68
    places
    -0.66
    indal
    -0.66
    ATOR
    -0.64
    iple
    -0.64
    rums
    -0.63
    POSITIVE LOGITS
     Upton
    0.94
     Mara
    0.93
     Wins
    0.92
    vich
    0.86
     Moss
    0.79
    y
    0.79
    fet
    0.78
    patrick
    0.76
     McCann
    0.73
     Bold
    0.73
    Activations Density 0.035%

    No Known Activations