© 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. 11958
    Prev
    Next
    INDEX
    Explanations

    instances of media-related phrases and criticisms involving Donald Trump

    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
    0:0.08
    1:0.09
    2:0.08
    3:0.05
    4:0.04
    5:0.04
    6:0.08
    7:0.09
    8:0.04
    9:0.08
    10:0.25
    11:0.03
    Negative Logits
     Sask
    -3.50
     Som
    -3.48
     Somali
    -3.39
     Somalia
    -3.23
     Afric
    -3.16
     Buch
    -3.15
     Gou
    -3.13
     Au
    -3.13
     Rasm
    -3.12
     Brav
    -3.12
    POSITIVE LOGITS
    cheon
    2.77
    Interested
    2.69
     trump
    2.62
    Trump
    2.50
     TRUMP
    2.44
     ty
    2.41
     Trump
    2.39
    tr
    2.35
    opes
    2.34
    ERAL
    2.33
    Activations Density 0.070%

    No Known Activations