© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 1493
    Prev
    Next
    INDEX
    Explanations

    content related to military and defense operations, particularly discussions about budget and efficiency within the Pentagon

    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
    0:0.13
    1:0.03
    2:0.14
    3:0.06
    4:0.04
    5:0.07
    6:0.05
    7:0.06
    8:0.25
    9:0.06
    10:0.03
    11:0.02
    Negative Logits
     Ulster
    -3.90
     Johannes
    -3.83
     Belfast
    -3.59
    Spain
    -3.57
     Sheffield
    -3.47
     Yorkshire
    -3.44
     Amsterdam
    -3.42
     Nottingham
    -3.35
     Delhi
    -3.33
     Catalonia
    -3.32
    POSITIVE LOGITS
     Pentagon
    6.38
     DOD
    5.81
     Defense
    4.12
     Lockheed
    4.07
     Medal
    3.88
     DAR
    3.74
     Marines
    3.71
     SEAL
    3.59
    Military
    3.56
     Navy
    3.55
    Activations Density 0.020%

    No Known Activations