© 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. 558
    Prev
    Next
    INDEX
    Explanations

    mentions of Russian sources or entities involved in alleged activities or communications

    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
    0:0.18
    1:0.03
    2:0.16
    3:0.07
    4:0.04
    5:0.08
    6:0.04
    7:0.07
    8:0.14
    9:0.03
    10:0.04
    11:0.05
    Negative Logits
     Boone
    -3.29
    keyes
    -3.29
     Haw
    -3.10
    erick
    -2.99
    imental
    -2.79
     Bland
    -2.77
    ggies
    -2.76
    byss
    -2.74
    wagon
    -2.73
     TCU
    -2.63
    POSITIVE LOGITS
    kaya
    4.75
     Ves
    4.24
     Sergei
    4.02
     Kremlin
    3.73
    afort
    3.69
     Kats
    3.62
    Russian
    3.40
     dossier
    3.39
     Kushner
    3.31
     incrim
    3.29
    Activations Density 0.004%

    No Known Activations