© 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. 9-ATT-KK
    11. 23842
    Prev
    Next
    INDEX
    Explanations

    instances of police-related incidents involving young black males

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.16
    1:0.02
    2:0.22
    3:0.10
    4:0.02
    5:0.12
    6:0.03
    7:0.05
    8:0.12
    9:0.02
    10:0.05
    11:0.03
    Negative Logits
     Zoro
    -2.82
     Witches
    -2.68
     witches
    -2.57
     maiden
    -2.48
     bunk
    -2.48
     Wyatt
    -2.47
    estern
    -2.47
     Outbreak
    -2.40
     IPM
    -2.38
    SHIP
    -2.37
    POSITIVE LOGITS
     grey
    3.07
     Ferguson
    2.95
     impulse
    2.83
     gray
    2.75
    erguson
    2.66
     disproportion
    2.60
     brown
    2.54
     unfocused
    2.51
     blurry
    2.48
     diffuse
    2.47
    Activations Density 0.035%

    No Known Activations