© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 21254
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest excellent qualities or significant achievements

    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
    0:0.04
    1:0.06
    2:0.03
    3:0.03
    4:0.06
    5:0.02
    6:0.03
    7:0.46
    8:0.02
    9:0.03
    10:0.04
    11:0.11
    Negative Logits
     Rocks
    -3.61
    rock
    -3.56
     ROCK
    -3.33
     Rock
    -3.28
    Rock
    -3.27
     rocks
    -3.12
    rences
    -2.93
    sand
    -2.93
     Rack
    -2.91
     rocking
    -2.81
    POSITIVE LOGITS
     Cunningham
    3.54
     NCT
    3.08
    umi
    3.05
     ACA
    2.80
    adobe
    2.78
     Cummings
    2.75
     Mehran
    2.73
     Browne
    2.72
     Flavoring
    2.71
     Clancy
    2.59
    Activations Density 0.007%

    No Known Activations