© 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. 17450
    Prev
    Next
    INDEX
    Explanations

    narrative elements related to conflicts or events involving resistance and the consequences following

    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
    0:0.18
    1:0.11
    2:0.10
    3:0.04
    4:0.04
    5:0.02
    6:0.06
    7:0.12
    8:0.04
    9:0.03
    10:0.17
    11:0.03
    Negative Logits
     Xperia
    -2.99
     iod
    -2.99
     iodine
    -2.94
     OU
    -2.90
     mart
    -2.85
     Kaz
    -2.61
     wrestlers
    -2.60
     Reign
    -2.57
     horm
    -2.52
    Lev
    -2.50
    POSITIVE LOGITS
     Fletcher
    8.91
    letcher
    5.50
     Sweeney
    3.87
     Bradford
    3.77
     Fowler
    3.72
     Eagles
    3.67
     Elliot
    3.35
    FP
    3.35
     Skinner
    3.28
     Finch
    3.26
    Activations Density 0.002%

    No Known Activations