© 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. 9542
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their roles

    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
    0:0.34
    1:0.05
    2:0.04
    3:0.10
    4:0.06
    5:0.02
    6:0.07
    7:0.08
    8:0.02
    9:0.06
    10:0.07
    11:0.04
    Negative Logits
     Mariners
    -4.21
     dispensary
    -3.93
     Kush
    -3.79
     Padres
    -3.68
    Redd
    -3.65
     indic
    -3.59
     Marijuana
    -3.51
    Yang
    -3.50
     Dwarf
    -3.49
    Arizona
    -3.47
    POSITIVE LOGITS
     Hollande
    7.46
     François
    7.10
     France
    6.80
     French
    6.73
     Marse
    6.71
    France
    6.66
    Paris
    6.59
     Francois
    6.47
     Macron
    6.46
    French
    6.42
    Activations Density 0.397%

    No Known Activations