© 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. 10853
    Prev
    Next
    INDEX
    Explanations

    references to Wisconsin and related events or studies

    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
    0:0.23
    1:0.04
    2:0.04
    3:0.08
    4:0.03
    5:0.01
    6:0.11
    7:0.13
    8:0.02
    9:0.03
    10:0.21
    11:0.03
    Negative Logits
    Egypt
    -4.68
     Malaysian
    -4.37
     Malaysia
    -4.22
     Narc
    -4.00
     Cambod
    -3.89
     Singapore
    -3.85
     Malays
    -3.84
     NEO
    -3.82
     Bangkok
    -3.67
     Nguyen
    -3.59
    POSITIVE LOGITS
     Wisconsin
    7.53
    Wisconsin
    7.41
     Milwaukee
    6.40
     WI
    5.79
    waukee
    5.74
    Madison
    5.73
     Manit
    5.73
     Madison
    5.67
     UW
    5.63
     Wis
    5.43
    Activations Density 0.047%

    No Known Activations