© 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. 3-RES-JB
    11. 8970
    Prev
    Next
    INDEX
    Explanations

    names related to the name "Kate"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Kate."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    notation
    -0.79
    cffff
    -0.79
    oresc
    -0.78
    ensed
    -0.76
    ATIONS
    -0.76
    ensical
    -0.72
    otin
    -0.72
    ribune
    -0.70
    cipl
    -0.70
    acists
    -0.70
    POSITIVE LOGITS
     Upton
    1.03
     Wins
    0.95
     McCann
    0.93
     Kate
    0.83
     Kane
    0.82
    vich
    0.82
     Turner
    0.82
     Stein
    0.82
     Beach
    0.81
     Hanna
    0.81
    Activations Density 0.004%

    No Known Activations