© 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. 6703
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and governance-related terms

    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
    0:0.40
    1:0.05
    2:0.05
    3:0.06
    4:0.05
    5:0.03
    6:0.05
    7:0.06
    8:0.02
    9:0.05
    10:0.07
    11:0.05
    Negative Logits
     Malays
    -5.07
     Malaysia
    -5.01
     Malaysian
    -4.92
     Kuala
    -4.45
     Webb
    -4.17
     Osiris
    -4.03
     Karachi
    -3.94
     Burma
    -3.80
     Manila
    -3.78
     Vegas
    -3.77
    POSITIVE LOGITS
     Milwaukee
    6.90
    Wisconsin
    6.83
     Wisconsin
    6.61
    Madison
    6.30
    waukee
    5.97
     WI
    5.92
     UW
    5.56
     Manit
    5.43
    Walker
    5.42
     Wis
    5.28
    Activations Density 0.033%

    No Known Activations