© 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. 0-RES-JB
    11. 7536
    Prev
    Next
    INDEX
    Explanations

    mentions of or related to girls

    oai_token-act-pair · gpt-3.5-turbo

    references to girls in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Component
    -0.75
     Gutenberg
    -0.66
    uron
    -0.64
    Mark
    -0.64
    urden
    -0.63
    License
    -0.63
     Render
    -0.61
    inct
    -0.61
    ulkan
    -0.60
    ector
    -0.60
    POSITIVE LOGITS
     girls
    3.63
    girls
    2.81
    Girls
    2.73
     Girls
    2.64
     boys
    2.55
     girl
    2.47
     females
    2.17
     daughters
    2.08
     women
    2.02
     ladies
    1.99
    Activations Density 0.020%

    No Known Activations