© 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. 12031
    Prev
    Next
    INDEX
    Explanations

    references to political events and historical narratives related to the presidency

    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
    0:0.27
    1:0.04
    2:0.04
    3:0.09
    4:0.07
    5:0.02
    6:0.11
    7:0.13
    8:0.02
    9:0.04
    10:0.06
    11:0.06
    Negative Logits
     Winnipeg
    -3.46
     �
    -3.32
     Boko
    -3.17
     Nigerian
    -3.15
     Typh
    -3.13
     Nigeria
    -3.12
     Pesh
    -3.10
     Vector
    -3.09
    ipeg
    -3.07
     ✔
    -3.04
    POSITIVE LOGITS
     Nixon
    8.27
     Watergate
    7.11
     Kissinger
    5.83
     1972
    4.22
    ixon
    4.14
     1973
    3.99
     Vietnam
    3.84
    CIA
    3.83
    1973
    3.81
     Reagan
    3.76
    Activations Density 0.010%

    No Known Activations