© 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. 10726
    Prev
    Next
    INDEX
    Explanations

    expressions of support and accountability towards law enforcement agencies

    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
    0:0.28
    1:0.03
    2:0.04
    3:0.07
    4:0.07
    5:0.03
    6:0.15
    7:0.11
    8:0.02
    9:0.05
    10:0.04
    11:0.05
    Negative Logits
     Zot
    -4.06
     centrif
    -3.79
     Dwarf
    -3.35
     reactor
    -3.29
     Dwar
    -3.29
     Mongolia
    -3.03
     reactors
    -2.96
     Vog
    -2.95
     uranium
    -2.93
    Recipe
    -2.92
    POSITIVE LOGITS
     NYPD
    5.89
     LAPD
    5.68
     policing
    5.45
     cops
    4.73
    police
    4.58
    erguson
    4.47
     homicides
    4.44
    Officers
    4.42
    Baltimore
    4.40
    APD
    4.33
    Activations Density 0.272%

    No Known Activations