© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-ATT-KK
    11. 11630
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases about local events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.03
    2:0.09
    3:0.15
    4:0.06
    5:0.07
    6:0.05
    7:0.05
    8:0.07
    9:0.02
    10:0.06
    11:0.04
    Negative Logits
     Ambrose
    -2.72
     reporting
    -2.62
     analyst
    -2.57
     Nielsen
    -2.55
     analysts
    -2.55
     Rowe
    -2.48
     indexes
    -2.47
     Moff
    -2.43
     judgments
    -2.42
     Eaton
    -2.33
    POSITIVE LOGITS
     Kickstarter
    3.80
    Kick
    3.36
    duino
    2.87
    PLA
    2.71
    ket
    2.69
     Desktop
    2.66
     Reincarn
    2.59
     Dice
    2.55
     Pledge
    2.53
    iHUD
    2.51
    Activations Density 0.003%

    No Known Activations