© 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. 19561
    Prev
    Next
    INDEX
    Explanations

    contextual references to military actions and the involvement of specific groups or individuals in conflict

    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
    0:0.19
    1:0.04
    2:0.07
    3:0.04
    4:0.05
    5:0.02
    6:0.10
    7:0.20
    8:0.02
    9:0.05
    10:0.11
    11:0.06
    Negative Logits
     Savannah
    -2.90
     IBM
    -2.72
     Bahamas
    -2.69
     Chero
    -2.66
     Cantor
    -2.65
     BCC
    -2.60
     Sandra
    -2.60
     Consumer
    -2.60
     Somerset
    -2.54
     Scotch
    -2.54
    POSITIVE LOGITS
     YPG
    5.52
     PKK
    3.64
    oğan
    3.10
     Kob
    2.95
     Erd
    2.91
     Raqqa
    2.89
    usra
    2.82
    YD
    2.77
     Ankara
    2.71
    Nusra
    2.68
    Activations Density 0.004%

    No Known Activations