© 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. 9-RES-JB
    11. 4148
    Prev
    Next
    INDEX
    Explanations

    mentions of young females, particularly in the context of relationships or societal roles

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "girl."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •female

    No Comments

    Negative Logits
    rehend
    -0.81
    psey
    -0.76
    raltar
    -0.74
    PDATE
    -0.73
    HAEL
    -0.72
    aeda
    -0.68
    odcast
    -0.68
    utherford
    -0.68
    arily
    -0.68
    fusc
    -0.68
    POSITIVE LOGITS
     Scouts
    0.99
    girl
    0.89
    girls
    0.88
     girls
    0.86
     panties
    0.86
    hood
    0.83
    bang
    0.82
     dolls
    0.80
    folk
    0.80
     herself
    0.78
    Activations Density 0.037%

    No Known Activations