© 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. 20162
    Prev
    Next
    INDEX
    Explanations

    phrases related to U.S. political positions and foreign policy concerning Israel

    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
    0:0.27
    1:0.04
    2:0.05
    3:0.11
    4:0.05
    5:0.02
    6:0.09
    7:0.09
    8:0.02
    9:0.05
    10:0.07
    11:0.07
    Negative Logits
     Silva
    -3.99
     Portuguese
    -3.80
     Vale
    -3.76
     Romanian
    -3.72
     Walton
    -3.68
     Kus
    -3.59
     Semin
    -3.51
     Mongo
    -3.48
     Bulgar
    -3.48
     Pyro
    -3.47
    POSITIVE LOGITS
    anyahu
    5.81
    Israel
    5.77
     Netanyahu
    5.73
     Israel
    5.41
    Israeli
    5.14
     Israelis
    5.00
     Zionism
    4.94
     Israeli
    4.76
     Judaism
    4.59
     Jewish
    4.43
    Activations Density 0.040%

    No Known Activations