© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 21823
    Prev
    Next
    INDEX
    Explanations

    references to espionage and surveillance activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.06
    2:0.14
    3:0.07
    4:0.06
    5:0.07
    6:0.03
    7:0.05
    8:0.07
    9:0.22
    10:0.08
    11:0.04
    Negative Logits
     adjustment
    -1.45
    ItemImage
    -1.29
     correction
    -1.27
     mathemat
    -1.21
     adjusted
    -1.17
    ukong
    -1.17
    ーク
    -1.15
     upward
    -1.14
    --------------------------------------------------------
    -1.13
     adjustments
    -1.13
    POSITIVE LOGITS
     spy
    1.61
     spies
    1.60
    alions
    1.51
     caches
    1.47
    ionage
    1.47
     KGB
    1.44
     detectors
    1.39
     decrypt
    1.37
    FBI
    1.37
     FBI
    1.37
    Activations Density 0.018%

    No Known Activations