© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19260
    Prev
    Next
    INDEX
    Explanations

    terms related to political relationships and attitudes towards Israel and Palestine

    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
    0:0.03
    1:0.03
    2:0.07
    3:0.03
    4:0.07
    5:0.04
    6:0.18
    7:0.05
    8:0.13
    9:0.24
    10:0.02
    11:0.05
    Negative Logits
     Gators
    -4.26
     Jackets
    -3.83
     Django
    -3.80
     Semin
    -3.77
     Wyn
    -3.67
    Florida
    -3.60
    buck
    -3.58
     Tampa
    -3.57
    atche
    -3.45
     Sabres
    -3.44
    POSITIVE LOGITS
     Netanyahu
    9.39
     Israelis
    9.31
    Israeli
    9.29
    Israel
    9.03
     Israel
    9.01
     Israeli
    9.00
    anyahu
    8.02
     IDF
    7.71
     Zionism
    7.03
     Zionist
    6.73
    Activations Density 0.081%

    No Known Activations