© 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. 12139
    Prev
    Next
    INDEX
    Explanations

    references to religious or cultural identities, particularly those related to Jewish communities

    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
    0:0.12
    1:0.07
    2:0.07
    3:0.12
    4:0.09
    5:0.04
    6:0.09
    7:0.10
    8:0.03
    9:0.06
    10:0.09
    11:0.06
    Negative Logits
     Palestinians
    -4.74
     Palestinian
    -4.38
     Arabs
    -4.29
    Palest
    -4.20
     Jews
    -4.04
     Israelis
    -3.94
    Palestinian
    -3.93
     Zionism
    -3.88
     Palestin
    -3.85
     Palestine
    -3.77
    POSITIVE LOGITS
     fentanyl
    2.90
    maxwell
    2.88
    entanyl
    2.83
    UFC
    2.77
     pokemon
    2.74
    coin
    2.73
    vantage
    2.72
    Alabama
    2.68
    elaide
    2.67
    FW
    2.63
    Activations Density 0.001%

    No Known Activations