© 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. 7523
    Prev
    Next
    INDEX
    Explanations

    phrases related to government and intelligence agency 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
    0:0.17
    1:0.04
    2:0.06
    3:0.11
    4:0.05
    5:0.03
    6:0.14
    7:0.11
    8:0.02
    9:0.06
    10:0.08
    11:0.06
    Negative Logits
     Sanford
    -3.74
     Omaha
    -3.44
     Chrysler
    -3.41
     Anaheim
    -3.31
     impeachment
    -3.31
     Heisman
    -3.31
     Oprah
    -3.28
     NCAA
    -3.27
     Cadillac
    -3.27
     Rockefeller
    -3.25
    POSITIVE LOGITS
    CHQ
    4.91
    Britain
    4.28
     Britain
    3.57
    ameron
    3.57
     RAF
    3.50
    ateurs
    3.47
     Britons
    3.33
    Scotland
    3.32
    UK
    3.28
     Trident
    3.20
    Activations Density 0.001%

    No Known Activations