© 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. 9-ATT-KK
    11. 6948
    Prev
    Next
    INDEX
    Explanations

    references to political leaders, particularly Donald Trump and Vladimir Putin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.04
    2:0.11
    3:0.20
    4:0.13
    5:0.10
    6:0.03
    7:0.05
    8:0.09
    9:0.02
    10:0.07
    11:0.05
    Negative Logits
     pubs
    -2.54
     Cinema
    -2.26
     nursery
    -2.21
     pub
    -2.18
     cottage
    -2.02
     toilets
    -2.01
     convent
    -2.01
     shelters
    -1.99
     castles
    -1.98
     workshops
    -1.94
    POSITIVE LOGITS
    uterte
    3.59
    kefeller
    3.31
    Obama
    3.28
     Obama
    3.27
    Trump
    3.17
    realDonaldTrump
    3.17
     Trump
    3.11
    ovych
    3.02
     Putin
    2.79
    President
    2.78
    Activations Density 0.045%

    No Known Activations