© 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. 13532
    Prev
    Next
    INDEX
    Explanations

    humor related to societal 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
    0:0.16
    1:0.08
    2:0.06
    3:0.15
    4:0.04
    5:0.03
    6:0.08
    7:0.09
    8:0.03
    9:0.04
    10:0.14
    11:0.05
    Negative Logits
     Georgian
    -3.12
     BlackBerry
    -3.06
     PW
    -3.04
    qt
    -3.03
    OUP
    -3.00
     phosphate
    -2.97
    ZI
    -2.97
     Hull
    -2.78
    uton
    -2.70
     Drone
    -2.68
    POSITIVE LOGITS
     Santa
    8.89
    Santa
    8.77
     Claus
    6.29
     elves
    4.46
     Sant
    4.08
    anta
    3.92
    Christmas
    3.86
    Christ
    3.78
    christ
    3.77
     SAN
    3.73
    Activations Density 0.025%

    No Known Activations