© 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. 9-ATT-KK
    11. 23481
    Prev
    Next
    INDEX
    Explanations

    mentions of Paul Manafort and his connections to the Kremlin

    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
    0:0.24
    1:0.01
    2:0.19
    3:0.08
    4:0.02
    5:0.10
    6:0.04
    7:0.03
    8:0.19
    9:0.01
    10:0.03
    11:0.01
    Negative Logits
     Slaughter
    -2.93
     cull
    -2.92
     Trout
    -2.79
     Hunger
    -2.72
     Manson
    -2.71
     Died
    -2.68
     Cricket
    -2.65
     carc
    -2.64
     Dawkins
    -2.64
     Tasman
    -2.63
    POSITIVE LOGITS
     Manafort
    6.32
    afort
    5.35
     Ukrainian
    4.86
     Ukraine
    4.85
     Yanukovych
    4.79
    Ukraine
    4.67
     Ukrainians
    4.53
     Kiev
    4.20
     Crimea
    4.15
    Uk
    3.92
    Activations Density 0.005%

    No Known Activations