© 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. 10888
    Prev
    Next
    INDEX
    Explanations

    the word "no"

    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
    0:0.15
    1:0.11
    2:0.08
    3:0.05
    4:0.04
    5:0.04
    6:0.10
    7:0.07
    8:0.04
    9:0.05
    10:0.18
    11:0.05
    Negative Logits
     CO
    -3.06
     Jacket
    -2.97
    ��
    -2.84
     Blanc
    -2.83
     ICE
    -2.82
     rotor
    -2.81
     Jackets
    -2.72
     LC
    -2.71
    crew
    -2.70
    chwitz
    -2.63
    POSITIVE LOGITS
     Tad
    9.28
     Tanz
    4.03
     Tanzania
    4.01
     Teddy
    3.94
     Wad
    3.92
     tad
    3.77
    dit
    3.50
     Nab
    3.48
     Dud
    3.43
     Tig
    3.37
    Activations Density 0.000%

    No Known Activations