© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 17275
    Prev
    Next
    INDEX
    Explanations

    references to clowns and circus-related themes

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.22
    1:0.10
    2:0.07
    3:0.03
    4:0.05
    5:0.02
    6:0.08
    7:0.09
    8:0.03
    9:0.04
    10:0.16
    11:0.06
    Negative Logits
    Ult
    -3.60
     UM
    -3.54
     Aus
    -3.39
     Ultr
    -3.24
     Ult
    -3.22
     Rw
    -3.21
     Ethiopian
    -3.15
     Ub
    -3.13
     Rwanda
    -3.00
     Wi
    -2.98
    POSITIVE LOGITS
     Clown
    9.45
     clown
    9.00
     Joker
    5.37
     Laugh
    4.47
     circus
    4.22
     Scare
    4.01
     Frog
    4.01
     Canaver
    3.89
     frog
    3.72
    alloween
    3.66
    Activations Density 0.008%

    No Known Activations