© 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. 10-ATT-KK
    11. 15288
    Prev
    Next
    INDEX
    Explanations

    phrases related to civilian casualties and violence in conflict situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.04
    2:0.04
    3:0.04
    4:0.09
    5:0.03
    6:0.04
    7:0.39
    8:0.03
    9:0.04
    10:0.03
    11:0.13
    Negative Logits
     Garry
    -2.68
     Browne
    -2.62
    userc
    -2.47
     Colombia
    -2.41
     humid
    -2.38
     Beaut
    -2.33
    ategor
    -2.31
     Neph
    -2.31
     mindfulness
    -2.29
     Feedback
    -2.24
    POSITIVE LOGITS
    ze
    2.88
    erk
    2.83
     Jak
    2.79
    zing
    2.77
    zes
    2.73
     Sik
    2.67
     XIII
    2.66
     Ezek
    2.57
    zed
    2.56
    iscons
    2.52
    Activations Density 0.005%

    No Known Activations