© 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. 14723
    Prev
    Next
    INDEX
    Explanations

    geographical references, particularly related to Brazil

    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
    0:0.08
    1:0.01
    2:0.07
    3:0.08
    4:0.02
    5:0.07
    6:0.03
    7:0.05
    8:0.48
    9:0.03
    10:0.03
    11:0.01
    Negative Logits
    Jewish
    -4.36
     Rabbi
    -4.07
     Shapiro
    -4.04
     Jewish
    -3.97
    Jew
    -3.97
     rabbi
    -3.83
    Jews
    -3.76
     Judaism
    -3.61
    chwitz
    -3.60
    Penn
    -3.59
    POSITIVE LOGITS
    Brazil
    8.54
     Brazilian
    8.13
     Brazil
    7.70
    ão
    7.50
     Sao
    6.98
     Portuguese
    6.39
     Bras
    6.20
    inho
    6.13
     Rio
    5.88
    ã
    5.80
    Activations Density 0.085%

    No Known Activations