© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14981
    Prev
    Next
    INDEX
    Explanations

    references to espionage and undercover operations

    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
    0:0.08
    1:0.02
    2:0.03
    3:0.05
    4:0.32
    5:0.05
    6:0.08
    7:0.10
    8:0.02
    9:0.08
    10:0.03
    11:0.09
    Negative Logits
     �
    -3.14
    �
    -2.89
    uture
    -2.82
     �
    -2.78
     �
    -2.69
    isSpecialOrderable
    -2.64
    �
    -2.63
    Crit
    -2.62
     Unsure
    -2.60
    .","
    -2.59
    POSITIVE LOGITS
     blackmail
    5.83
     extortion
    5.30
     bribes
    5.23
     clandestine
    5.19
     bribe
    5.09
     disgu
    5.06
     undercover
    5.02
     faked
    4.98
     smuggling
    4.95
     counterfe
    4.94
    Activations Density 1.027%

    No Known Activations