© 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. 5272
    Prev
    Next
    INDEX
    Explanations

    references to civilian casualties and related statistics in conflict contexts

    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
    0:0.10
    1:0.03
    2:0.18
    3:0.07
    4:0.04
    5:0.09
    6:0.11
    7:0.07
    8:0.09
    9:0.09
    10:0.04
    11:0.02
    Negative Logits
     Wick
    -3.08
     Sugar
    -2.81
     Zig
    -2.72
     Rhythm
    -2.69
     Phillips
    -2.64
     Rodgers
    -2.61
     Spa
    -2.56
     Euros
    -2.52
     Schn
    -2.47
    kiss
    -2.47
    POSITIVE LOGITS
     civilian
    6.19
     civilians
    5.81
     airstrike
    3.86
     munitions
    3.83
     combatants
    3.76
     casualty
    3.65
    combat
    3.60
     airstrikes
    3.43
     bombed
    3.42
     humanitarian
    3.41
    Activations Density 0.023%

    No Known Activations