© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15527
    Prev
    Next
    INDEX
    Explanations

    mentions of presidential actions and controversies related to key events and figures in politics

    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
    0:0.33
    1:0.04
    2:0.06
    3:0.07
    4:0.08
    5:0.03
    6:0.11
    7:0.06
    8:0.02
    9:0.06
    10:0.05
    11:0.04
    Negative Logits
     Cann
    -3.90
     Henderson
    -3.69
     Flam
    -3.67
     Lizard
    -3.67
     Barker
    -3.54
     Smy
    -3.51
     frogs
    -3.47
     frog
    -3.38
     Frem
    -3.31
     Beetle
    -3.28
    POSITIVE LOGITS
    Obama
    5.16
     Kenyan
    5.03
     Obama
    4.20
     Kenya
    4.04
     Somali
    3.95
    Chicago
    3.73
     Barack
    3.69
    clinton
    3.59
    Michelle
    3.57
     bir
    3.55
    Activations Density 0.049%

    No Known Activations