© 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. 10-ATT-KK
    11. 14439
    Prev
    Next
    INDEX
    Explanations

    references to characters and their attributes in popular culture

    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
    0:0.26
    1:0.04
    2:0.07
    3:0.07
    4:0.06
    5:0.02
    6:0.09
    7:0.16
    8:0.02
    9:0.06
    10:0.07
    11:0.02
    Negative Logits
    Pakistan
    -3.67
     Karachi
    -3.62
     Vietnam
    -3.41
    uterte
    -3.31
     Bangalore
    -3.20
     Pakistan
    -3.16
     Philippine
    -3.11
     ISI
    -3.10
     NBN
    -3.09
    Pak
    -3.08
    POSITIVE LOGITS
     Elsa
    7.87
    Elsa
    6.96
     Anna
    6.15
    Anna
    5.67
     Frozen
    5.32
     Krist
    4.64
     Sven
    4.37
    Krist
    4.17
    rozen
    4.16
     icy
    4.11
    Activations Density 0.007%

    No Known Activations