© 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. 9142
    Prev
    Next
    INDEX
    Explanations

    references to North Korea and its political or military activities

    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
    0:0.11
    1:0.04
    2:0.04
    3:0.09
    4:0.06
    5:0.04
    6:0.06
    7:0.09
    8:0.03
    9:0.07
    10:0.28
    11:0.06
    Negative Logits
     Philippine
    -4.38
     Bosnia
    -4.14
     Manila
    -4.11
     Azerbai
    -3.72
     Azerbaijan
    -3.64
     Philippines
    -3.63
     Colombia
    -3.62
     Slovenia
    -3.61
    Brazil
    -3.39
     Belarus
    -3.33
    POSITIVE LOGITS
    NK
    4.15
     NK
    3.28
     K
    3.09
    K
    3.02
     KD
    2.83
     Appeal
    2.69
    KC
    2.65
    uscript
    2.54
     Ker
    2.52
     Kh
    2.49
    Activations Density 0.006%

    No Known Activations