© 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. 12030
    Prev
    Next
    INDEX
    Explanations

    references to protests and societal issues involving government actions and community responses

    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
    0:0.19
    1:0.05
    2:0.04
    3:0.10
    4:0.04
    5:0.01
    6:0.10
    7:0.11
    8:0.01
    9:0.03
    10:0.23
    11:0.03
    Negative Logits
     JFK
    -3.35
     Luigi
    -2.99
     Madagascar
    -2.95
     Ramos
    -2.94
     Tunis
    -2.89
     Palest
    -2.87
    Ko
    -2.73
     bunny
    -2.73
    arten
    -2.71
     Jungle
    -2.70
    POSITIVE LOGITS
     Sask
    9.18
     Saskatchewan
    8.72
     Regina
    6.94
    atchewan
    6.05
     Calgary
    4.73
     Winnipeg
    4.72
     Alberta
    4.70
     Edmonton
    4.65
    ipeg
    4.43
     Manitoba
    4.42
    Activations Density 0.007%

    No Known Activations