© 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. 1926
    Prev
    Next
    INDEX
    Explanations

    discourses surrounding immigration and multiculturalism

    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
    0:0.05
    1:0.03
    2:0.05
    3:0.05
    4:0.06
    5:0.06
    6:0.20
    7:0.06
    8:0.06
    9:0.25
    10:0.04
    11:0.04
    Negative Logits
     Flare
    -3.86
    phi
    -3.81
     Hera
    -3.56
    Ari
    -3.40
    Hamilton
    -3.40
     Floyd
    -3.39
     Mayweather
    -3.38
     Viper
    -3.29
    Hop
    -3.28
    oyd
    -3.27
    POSITIVE LOGITS
     Sweden
    7.53
     Swed
    7.04
     Swedish
    6.72
     Scandinav
    6.19
     Stockholm
    6.04
     Scandinavian
    5.59
    å
    5.34
     Nordic
    5.21
     Sven
    4.77
    Sw
    4.51
    Activations Density 0.006%

    No Known Activations