© 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. 20606
    Prev
    Next
    INDEX
    Explanations

    mentions of performances and stunts involving aerial acts

    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
    0:0.03
    1:0.02
    2:0.12
    3:0.07
    4:0.07
    5:0.27
    6:0.02
    7:0.03
    8:0.02
    9:0.23
    10:0.03
    11:0.05
    Negative Logits
     varies
    -2.79
     cannot
    -2.78
    erred
    -2.77
     depends
    -2.76
     differs
    -2.73
     disagrees
    -2.71
     determines
    -2.70
     disputed
    -2.63
     persists
    -2.54
     expires
    -2.47
    POSITIVE LOGITS
     whilst
    3.33
     toget
    3.14
     �
    2.99
     �
    2.97
     tremend
    2.92
     extraord
    2.81
     backstage
    2.81
     himself
    2.75
     showcasing
    2.74
     his
    2.74
    Activations Density 0.904%

    No Known Activations