© 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. 20370
    Prev
    Next
    INDEX
    Explanations

    narratives involving political figures and their connections within government and media

    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
    0:0.17
    1:0.01
    2:0.16
    3:0.08
    4:0.03
    5:0.08
    6:0.06
    7:0.06
    8:0.22
    9:0.04
    10:0.02
    11:0.02
    Negative Logits
    elaide
    -4.04
    byss
    -3.94
     Adelaide
    -3.50
     Ada
    -3.28
     Austral
    -3.16
     beetles
    -3.15
     Jagu
    -3.02
     Anarchy
    -3.00
     Augusta
    -2.96
    ufact
    -2.93
    POSITIVE LOGITS
     Kushner
    8.66
     Jared
    5.20
     Ivanka
    4.58
    arov
    3.98
     Kislyak
    3.86
     rabbi
    3.83
     Kush
    3.77
    Iv
    3.76
     Jewish
    3.64
    Israeli
    3.63
    Activations Density 0.011%

    No Known Activations