© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 13584
    Prev
    Next
    INDEX
    Explanations

    indicators of sarcasm and humor in references to social issues

    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
    3:0.09
    4:0.03
    5:0.05
    6:0.10
    7:0.03
    8:0.04
    9:0.34
    10:0.05
    11:0.07
    Negative Logits
     Cable
    -4.20
     Chavez
    -3.73
     Mous
    -3.39
     Mug
    -3.36
     marsh
    -3.27
     Curry
    -3.19
     Hercules
    -3.06
     Saber
    -3.02
     Moss
    -3.01
     Worm
    -3.01
    POSITIVE LOGITS
    �
    5.40
     Flo
    4.11
    �
    3.83
    ל
    3.78
    の魔
    3.49
     Lowell
    3.47
    ゴン
    3.47
     Fla
    3.37
    -|
    3.37
    pa
    3.32
    Activations Density 0.432%

    No Known Activations