© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 7179
    Prev
    Next
    INDEX
    Explanations

    mentions of public officials and law enforcement figures in the context of news articles

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.31
    1:0.05
    2:0.07
    3:0.08
    4:0.05
    5:0.03
    6:0.06
    7:0.07
    8:0.02
    9:0.04
    10:0.13
    11:0.04
    Negative Logits
     tidal
    -3.77
     steam
    -3.75
     Rapids
    -3.73
     Arbor
    -3.60
     Boston
    -3.57
     Brock
    -3.42
     Erie
    -3.41
     Swim
    -3.39
    River
    -3.39
     Worcester
    -3.39
    POSITIVE LOGITS
     Wraith
    4.92
     Romo
    4.76
     Cowboys
    4.58
    Dallas
    4.52
    SG
    4.16
     Starg
    4.02
     Ezekiel
    3.98
     Prescott
    3.94
     Mavericks
    3.81
     Boyd
    3.65
    Activations Density 0.012%

    No Known Activations