© 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. 9-ATT-KK
    11. 5622
    Prev
    Next
    INDEX
    Explanations

    references to authority figures or titles, particularly in legal and political contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.10
    1:0.02
    2:0.06
    3:0.22
    4:0.03
    5:0.07
    6:0.04
    7:0.04
    8:0.27
    9:0.02
    10:0.05
    11:0.04
    Negative Logits
    ı
    -3.94
    ğ
    -3.35
    �
    -3.31
    �
    -3.19
     Nieto
    -3.17
    Ã
    -3.11
     Ü
    -3.06
    ö
    -3.04
     Ö
    -3.02
    ocumented
    -2.92
    POSITIVE LOGITS
     Lords
    4.81
     Lord
    4.71
    Lord
    4.52
     Somerset
    3.90
     lords
    3.89
     Churchill
    3.79
     Welsh
    3.65
     Westminster
    3.63
     Wales
    3.61
    England
    3.54
    Activations Density 0.003%

    No Known Activations