© 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. 13688
    Prev
    Next
    INDEX
    Explanations

    references to significant events and entities related to the Rio Olympics

    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
    0:0.22
    1:0.06
    2:0.03
    3:0.05
    4:0.02
    5:0.02
    6:0.07
    7:0.22
    8:0.03
    9:0.04
    10:0.13
    11:0.06
    Negative Logits
     Shapiro
    -2.88
     Vader
    -2.70
     Pars
    -2.54
     Levin
    -2.51
     Hughes
    -2.46
     Koen
    -2.45
     Syracuse
    -2.41
     Maple
    -2.41
    Hug
    -2.39
     Yankee
    -2.38
    POSITIVE LOGITS
     Rio
    4.51
     Guan
    3.67
     Athlet
    3.43
     Janeiro
    3.04
     Confeder
    2.97
    Brazil
    2.89
    inho
    2.84
     Brazil
    2.81
     Rousse
    2.79
     Bras
    2.78
    Activations Density 0.008%

    No Known Activations