© 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. 7902
    Prev
    Next
    INDEX
    Explanations

    phrases and discussions revolving around the military budget and associated spending issues

    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
    0:0.15
    1:0.05
    2:0.04
    3:0.06
    4:0.05
    5:0.02
    6:0.22
    7:0.12
    8:0.02
    9:0.06
    10:0.10
    11:0.06
    Negative Logits
     Nadu
    -3.38
     Catalonia
    -3.21
     Sharma
    -3.18
     Leica
    -3.13
     Ulster
    -3.04
     Catalan
    -3.04
     Winc
    -2.87
     Qué
    -2.85
     Sammy
    -2.79
    Ont
    -2.73
    POSITIVE LOGITS
     Pentagon
    6.72
     DOD
    6.26
     Defense
    4.93
     Lockheed
    3.96
     USAF
    3.93
    Defense
    3.90
     DAR
    3.89
     Dempsey
    3.77
     RAND
    3.65
     Mattis
    3.64
    Activations Density 0.019%

    No Known Activations