© 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. 11934
    Prev
    Next
    INDEX
    Explanations

    instances of legal and judicial proceedings

    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
    0:0.21
    1:0.06
    2:0.10
    3:0.05
    4:0.02
    5:0.04
    6:0.08
    7:0.12
    8:0.02
    9:0.04
    10:0.16
    11:0.04
    Negative Logits
     Siberian
    -3.23
    hent
    -3.11
     Tud
    -2.92
     Kinect
    -2.86
     Bent
    -2.76
     EPS
    -2.74
     shampoo
    -2.70
    Ry
    -2.67
     freshwater
    -2.63
     Siberia
    -2.60
    POSITIVE LOGITS
     Garcia
    9.76
     Garc
    6.10
     Grateful
    4.67
    Gi
    4.21
     Gonzalez
    4.09
     Gibraltar
    4.07
    ía
    3.89
     Gomez
    3.87
     Pablo
    3.80
     Diego
    3.75
    Activations Density 0.007%

    No Known Activations