© 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. 10-ATT-KK
    11. 8665
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their occurrences in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.14
    2:0.04
    3:0.09
    4:0.05
    5:0.03
    6:0.10
    7:0.16
    8:0.05
    9:0.05
    10:0.09
    11:0.06
    Negative Logits
     Ferdinand
    -3.07
     Portuguese
    -2.81
     Fernand
    -2.74
     Moor
    -2.63
     Manchester
    -2.54
     Mourinho
    -2.54
     Croat
    -2.51
     Ukip
    -2.47
     Rooney
    -2.45
     Marcos
    -2.42
    POSITIVE LOGITS
     [&
    2.95
    arsity
    2.91
    uberty
    2.88
    uncture
    2.86
    lycer
    2.67
    amsung
    2.65
    phrine
    2.64
    bike
    2.61
     rapp
    2.60
     bikes
    2.60
    Activations Density 0.001%

    No Known Activations