© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 9870
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geopolitical tensions and conflicts, particularly regarding Israel and Palestine

    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
    0:0.30
    1:0.04
    2:0.04
    3:0.13
    4:0.07
    5:0.01
    6:0.08
    7:0.08
    8:0.02
    9:0.03
    10:0.10
    11:0.04
    Negative Logits
     Gators
    -4.77
    Florida
    -4.66
     Daytona
    -4.35
     pokemon
    -4.25
    mson
    -4.25
     Semin
    -3.94
     Django
    -3.86
     Saras
    -3.84
     Florida
    -3.80
    ernand
    -3.79
    POSITIVE LOGITS
     Israeli
    9.62
     Israelis
    9.59
    Israeli
    9.51
    Israel
    9.23
     Palestinian
    9.18
     Israel
    9.17
     Palestinians
    9.08
    Palest
    9.01
    Palestinian
    8.90
     Zionism
    8.81
    Activations Density 0.888%

    No Known Activations