© 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. 10-ATT-KK
    11. 22912
    Prev
    Next
    INDEX
    Explanations

    events related to violence and casualties in Afghanistan, particularly involving terrorism and the Taliban

    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
    0:0.32
    1:0.04
    2:0.04
    3:0.09
    4:0.05
    5:0.02
    6:0.08
    7:0.11
    8:0.01
    9:0.05
    10:0.11
    11:0.03
    Negative Logits
     Galileo
    -4.42
     cider
    -4.16
    Catal
    -3.99
     Pelicans
    -3.98
     Cavs
    -3.92
     Livingston
    -3.86
     Cavaliers
    -3.76
     Galile
    -3.64
     Catalan
    -3.56
     Valencia
    -3.47
    POSITIVE LOGITS
     Kabul
    9.74
     Afghan
    9.49
     Afghans
    9.32
     Taliban
    8.69
     Afghanistan
    8.39
     Afgh
    7.70
    Af
    6.95
     Kand
    6.57
    zai
    6.56
     Kund
    6.52
    Activations Density 0.144%

    No Known Activations