© 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. 9-ATT-KK
    11. 8313
    Prev
    Next
    INDEX
    Explanations

    sequences of punctuation and specific structural elements in the text

    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
    0:0.13
    1:0.01
    2:0.06
    3:0.04
    4:0.03
    5:0.05
    6:0.26
    7:0.05
    8:0.07
    9:0.22
    10:0.02
    11:0.02
    Negative Logits
     Az
    -4.75
     val
    -4.53
    Az
    -4.22
    ć
    -3.81
     Zar
    -3.79
     Warcraft
    -3.73
     py
    -3.72
     sor
    -3.62
     Spell
    -3.58
    oké
    -3.54
    POSITIVE LOGITS
     Hutchinson
    10.14
     Hudson
    7.08
     Hutch
    6.00
     Dawson
    4.03
    Hug
    4.01
     Hawk
    3.97
     Hut
    3.94
     Harding
    3.85
     Hansen
    3.85
     Howe
    3.81
    Activations Density 0.003%

    No Known Activations