© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 6882
    Prev
    Next
    INDEX
    Explanations

    references to cultural stereotypes about Asian men

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.19
    1:0.15
    2:0.04
    3:0.17
    4:0.03
    5:0.01
    6:0.04
    7:0.12
    8:0.01
    9:0.03
    10:0.10
    11:0.04
    Negative Logits
    esson
    -2.92
    hof
    -2.92
    conom
    -2.89
     MPG
    -2.87
     Wasteland
    -2.86
     Rutherford
    -2.82
    ibel
    -2.74
     Sabb
    -2.72
    lehem
    -2.71
     Elias
    -2.70
    POSITIVE LOGITS
     Asian
    8.52
    Asian
    8.23
     Asians
    7.99
     Taiwanese
    5.83
     Asia
    5.66
     Korean
    5.50
     Chinese
    5.50
    Chinese
    5.48
     Oriental
    5.41
     Chinatown
    5.41
    Activations Density 0.066%

    No Known Activations