© 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. 21072
    Prev
    Next
    INDEX
    Explanations

    phrases about repetition and frequency in contexts such as writing or customer interactions

    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
    0:0.07
    1:0.18
    2:0.07
    3:0.18
    4:0.07
    5:0.02
    6:0.06
    7:0.10
    8:0.03
    9:0.03
    10:0.07
    11:0.06
    Negative Logits
    intel
    -2.69
     Strait
    -2.50
     totem
    -2.38
     Bog
    -2.37
     Totem
    -2.34
     Bowen
    -2.32
     Anita
    -2.31
    Fair
    -2.30
     Booth
    -2.30
    perty
    -2.29
    POSITIVE LOGITS
     repeat
    6.78
     Repeat
    6.01
    repeat
    5.67
     repeats
    5.57
    Repeat
    5.51
     repeating
    5.11
     repeated
    4.96
     repetition
    4.42
    repe
    3.88
     repet
    3.64
    Activations Density 0.003%

    No Known Activations