© 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. 12836
    Prev
    Next
    INDEX
    Explanations

    concepts related to government surveillance and intelligence 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
    0:0.27
    1:0.03
    2:0.05
    3:0.06
    4:0.10
    5:0.02
    6:0.15
    7:0.09
    8:0.02
    9:0.04
    10:0.05
    11:0.08
    Negative Logits
     Wrest
    -3.29
     paddle
    -3.27
     sculpt
    -3.11
    Pain
    -3.07
     derby
    -2.99
    Sty
    -2.95
     Fraz
    -2.90
    nutrition
    -2.89
     Vegan
    -2.83
    Unity
    -2.79
    POSITIVE LOGITS
     NSA
    7.83
    NSA
    7.71
     Snowden
    7.41
     FISA
    6.82
     spying
    6.55
     wiret
    6.04
     surveillance
    5.92
     eaves
    5.83
     Surveillance
    5.83
     spy
    5.82
    Activations Density 0.554%

    No Known Activations