© 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. 23069
    Prev
    Next
    INDEX
    Explanations

    comparisons between different films and characters in cinema

    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
    2:0.09
    3:0.05
    4:0.04
    5:0.02
    6:0.07
    7:0.11
    8:0.02
    9:0.03
    10:0.12
    11:0.07
    Negative Logits
     Stamford
    -3.21
    Redd
    -3.20
     Fernandez
    -2.87
     Rivera
    -2.86
     Mahm
    -2.84
     Fernando
    -2.81
     Saras
    -2.79
    pton
    -2.77
     parachute
    -2.76
     Torres
    -2.75
    POSITIVE LOGITS
     Beast
    7.48
    Beast
    6.97
     Beasts
    6.56
     beast
    5.65
     beasts
    4.65
     herds
    3.87
    wolves
    3.76
     wolf
    3.69
     Bear
    3.63
     Belle
    3.62
    Activations Density 0.004%

    No Known Activations