© 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. 4883
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequency

    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
    0:0.08
    1:0.02
    2:0.05
    3:0.04
    4:0.04
    5:0.03
    6:0.22
    7:0.04
    8:0.06
    9:0.32
    10:0.02
    11:0.03
    Negative Logits
    LL
    -4.42
     Ll
    -3.88
     LL
    -3.78
    ocks
    -3.75
    LOCK
    -3.71
     tether
    -3.66
    amsung
    -3.55
    hurst
    -3.48
    Luke
    -3.44
     Hilton
    -3.41
    POSITIVE LOGITS
     Fran
    9.78
    Fran
    8.48
     Franco
    7.24
     Franz
    5.83
     Franks
    4.27
     Fra
    4.25
     Fren
    4.25
     Zin
    4.07
     Russo
    4.04
     Franç
    4.03
    Activations Density 0.001%

    No Known Activations