© 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. 9-ATT-KK
    11. 23309
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "originally appeared" signaling references to source material or citations

    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
    0:0.12
    1:0.01
    2:0.05
    3:0.16
    4:0.03
    5:0.12
    6:0.01
    7:0.14
    8:0.05
    9:0.01
    10:0.23
    11:0.02
    Negative Logits
     balloons
    -1.86
     unilaterally
    -1.75
     stret
    -1.75
     inaug
    -1.72
     arbitrarily
    -1.72
     glimps
    -1.59
     slightest
    -1.56
     passengers
    -1.56
     anytime
    -1.56
    displayText
    -1.55
    POSITIVE LOGITS
    sonian
    1.97
    olicy
    1.94
     Thinking
    1.88
     Writing
    1.83
     Nerd
    1.81
    Rated
    1.81
     Vegan
    1.78
    advertisement
    1.78
     Wanted
    1.76
    Edited
    1.73
    Activations Density 0.015%

    No Known Activations