© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 9358
    Prev
    Next
    INDEX
    Explanations

    references to societal issues impacting boys and girls, particularly in education and representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.03
    2:0.15
    3:0.04
    4:0.06
    5:0.04
    6:0.30
    7:0.07
    8:0.03
    9:0.11
    10:0.02
    11:0.02
    Negative Logits
     Berman
    -3.79
    veland
    -3.61
     Watergate
    -3.60
     Ferguson
    -3.56
     Manit
    -3.44
     Berm
    -3.43
    orne
    -3.40
     Carpenter
    -3.34
     Rutherford
    -3.29
    erguson
    -3.24
    POSITIVE LOGITS
     Girls
    9.13
    Girls
    9.06
     girls
    8.77
    girls
    7.78
     Girl
    7.56
     girl
    7.14
    Girl
    6.95
    girl
    6.20
     Boys
    6.13
     boys
    6.08
    Activations Density 0.076%

    No Known Activations