© 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. 9060
    Prev
    Next
    INDEX
    Explanations

    references to espionage, intelligence operations, and associated covert actions

    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
    0:0.11
    1:0.02
    2:0.17
    3:0.14
    4:0.05
    5:0.15
    6:0.02
    7:0.09
    8:0.09
    9:0.02
    10:0.05
    11:0.03
    Negative Logits
    ciation
    -2.38
    TPPStreamerBot
    -2.20
    inventoryQuantity
    -2.19
    Parent
    -2.09
    Gender
    -2.05
     dads
    -2.01
    �
    -1.99
    ukemia
    -1.99
     breastfeeding
    -1.98
    oother
    -1.96
    POSITIVE LOGITS
     KGB
    4.08
     spies
    4.07
     espionage
    4.06
     covert
    3.79
     informants
    3.73
     spy
    3.67
     CIA
    3.52
     clandestine
    3.45
     informant
    3.40
     spying
    3.37
    Activations Density 0.722%

    No Known Activations