© 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. 13777
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of females, specifically the word "girl" or "girls."

    oai_token-act-pair · gpt-3.5-turbo

    references to female characters or individuals described as girls

    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
    •Female Descriptors

    No Comments

    Negative Logits
    utherford
    -0.75
    raltar
    -0.74
    SPONSORED
    -0.74
    glas
    -0.73
    PDATE
    -0.72
    nce
    -0.72
    psey
    -0.72
    HAEL
    -0.72
    fusc
    -0.70
    rehens
    -0.69
    POSITIVE LOGITS
     panties
    1.10
     girls
    1.01
    girls
    1.01
    girl
    0.99
     dolls
    0.95
     girl
    0.89
    Girls
    0.87
     sisters
    0.87
     herself
    0.86
     Ivanka
    0.84
    Activations Density 0.081%

    No Known Activations