© 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. 12947
    Prev
    Next
    INDEX
    Explanations

    instances of law enforcement-related events or actions

    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
    0:0.05
    1:0.27
    2:0.04
    3:0.23
    4:0.02
    5:0.01
    6:0.04
    7:0.07
    8:0.01
    9:0.03
    10:0.13
    11:0.03
    Negative Logits
     Minotaur
    -2.70
    ヴァ
    -2.62
    Split
    -2.60
    MpServer
    -2.50
    govtrack
    -2.44
    externalActionCode
    -2.42
    cius
    -2.41
     Perse
    -2.33
     Cla
    -2.33
    atical
    -2.30
    POSITIVE LOGITS
     West
    8.73
    West
    8.21
    west
    5.40
     East
    5.35
     west
    5.19
    East
    4.78
     Western
    4.19
    east
    4.00
    Western
    3.61
     east
    3.58
    Activations Density 0.093%

    No Known Activations