© 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. 12225
    Prev
    Next
    INDEX
    Explanations

    references to historical events related to Mao Zedong and his ideological impact

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.16
    1:0.04
    2:0.06
    3:0.10
    4:0.06
    5:0.03
    6:0.13
    7:0.14
    8:0.02
    9:0.07
    10:0.09
    11:0.06
    Negative Logits
    Scot
    -3.06
    etsy
    -2.96
     Kraken
    -2.93
     Philips
    -2.87
    Philadelphia
    -2.81
     McKay
    -2.80
    lando
    -2.79
     benz
    -2.75
     Danish
    -2.74
    Scotland
    -2.72
    POSITIVE LOGITS
     Mao
    6.66
     Liu
    4.28
     Jiang
    4.16
     Communist
    3.94
     communists
    3.73
     Lenin
    3.73
     Zhou
    3.72
     Deng
    3.71
     Communists
    3.71
    Lenin
    3.68
    Activations Density 0.011%

    No Known Activations