© 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. 5-ATT-KK
    11. 30116
    Prev
    Next
    INDEX
    Explanations

    phrases indicating positions or titles of individuals in a committee or legislative context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.08
    1:0.05
    2:0.08
    3:0.06
    4:0.06
    5:0.04
    6:0.03
    7:0.03
    8:0.03
    9:0.10
    10:0.33
    11:0.05
    Negative Logits
    hyde
    -1.78
    zb
    -1.78
     0004
    -1.77
     Eternal
    -1.72
     foreskin
    -1.72
    tale
    -1.69
    DragonMagazine
    -1.68
     Spo
    -1.67
     unfolds
    -1.66
    tips
    -1.66
    POSITIVE LOGITS
     voting
    2.40
     caucus
    2.15
     voted
    2.09
     elected
    2.09
     filibuster
    2.05
     Caucus
    2.02
    aucus
    2.01
     vote
    1.94
     nominate
    1.90
     Voting
    1.88
    Activations Density 0.015%

    No Known Activations