© 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. 19957
    Prev
    Next
    INDEX
    Explanations

    discussions about doubt and attention in relation to a character named Constantine

    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
    0:0.20
    1:0.08
    2:0.08
    3:0.07
    4:0.05
    5:0.03
    6:0.15
    7:0.10
    8:0.02
    9:0.04
    10:0.09
    11:0.03
    Negative Logits
    �
    -3.41
     sax
    -3.17
     Malays
    -3.01
    iku
    -2.88
     Brune
    -2.83
    aez
    -2.74
    oot
    -2.70
    ********
    -2.69
     JD
    -2.66
     ANC
    -2.66
    POSITIVE LOGITS
     Constantine
    8.77
     Constantin
    4.58
     Hades
    3.81
     Lep
    3.73
     Constantinople
    3.64
     Conan
    3.59
     Dracula
    3.50
     Lucifer
    3.49
     Mith
    3.37
     Zeus
    3.27
    Activations Density 0.001%

    No Known Activations