© 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. 21087
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequency to indicate structure or emphasis 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
    0:0.07
    1:0.11
    2:0.06
    3:0.04
    4:0.04
    5:0.04
    6:0.19
    7:0.03
    8:0.06
    9:0.24
    10:0.02
    11:0.03
    Negative Logits
     Tes
    -3.68
     Dock
    -3.64
    Tes
    -3.61
     Paras
    -3.34
    aux
    -3.31
     aux
    -3.31
     darts
    -3.28
    des
    -3.25
    ilib
    -3.19
    Stock
    -3.19
    POSITIVE LOGITS
     Roh
    7.62
     OH
    5.71
    oh
    5.67
     Joh
    5.50
     Holy
    5.29
     Oh
    5.14
     Koh
    4.80
    OH
    4.76
     oh
    4.75
     Boh
    4.58
    Activations Density 0.002%

    No Known Activations