© 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. 13744
    Prev
    Next
    INDEX
    Explanations

    expressions indicating investigation or inquiry regarding important social issues

    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
    0:0.29
    1:0.04
    2:0.03
    3:0.10
    4:0.06
    5:0.02
    6:0.08
    7:0.10
    8:0.02
    9:0.03
    10:0.15
    11:0.03
    Negative Logits
     Padres
    -4.45
    Lua
    -4.11
     Raiders
    -3.84
     Marlins
    -3.79
    Snake
    -3.77
     Lua
    -3.71
     Rays
    -3.68
     DPRK
    -3.66
     Tanaka
    -3.54
     Dolphins
    -3.44
    POSITIVE LOGITS
     Belgian
    8.88
     Belgium
    8.54
     Belg
    8.43
     Brussels
    6.97
     Luxembourg
    4.95
    Bel
    4.71
     Bru
    4.60
     Serbia
    4.33
     Serbian
    4.00
     Philippe
    3.92
    Activations Density 0.026%

    No Known Activations