© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 17403
    Prev
    Next
    INDEX
    Explanations

    capitalization patterns typically associated with names and titles

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.14
    1:0.20
    2:0.04
    3:0.04
    4:0.03
    5:0.02
    6:0.06
    7:0.15
    8:0.04
    9:0.03
    10:0.15
    11:0.07
    Negative Logits
     Aad
    -3.05
    oday
    -2.48
    フォ
    -2.38
     Rak
    -2.38
     Braves
    -2.33
     Hyundai
    -2.25
     NFC
    -2.25
     seeded
    -2.21
     Salvation
    -2.21
     HAL
    -2.21
    POSITIVE LOGITS
    ux
    5.39
    UX
    4.08
    lux
    3.98
     Lux
    3.54
     Sussex
    2.97
     Surrey
    2.88
    Mac
    2.86
    tu
    2.82
     Scotch
    2.78
     Xie
    2.78
    Activations Density 0.002%

    No Known Activations