© 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. 19378
    Prev
    Next
    INDEX
    Explanations

    instances of significant individuals and notable events

    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
    0:0.11
    1:0.04
    2:0.09
    3:0.04
    4:0.03
    5:0.03
    6:0.25
    7:0.03
    8:0.03
    9:0.24
    10:0.02
    11:0.03
    Negative Logits
     Hispan
    -3.92
     Sev
    -3.70
    MRI
    -3.42
     Mecca
    -3.42
     NW
    -3.41
     Portug
    -3.37
    915
    -3.36
    arn
    -3.33
     Cogn
    -3.32
     Romero
    -3.29
    POSITIVE LOGITS
    Drop
    7.41
    drop
    7.20
     Dro
    7.01
     Drop
    6.79
    drops
    6.69
     drop
    6.66
    dro
    6.65
    Dro
    6.61
     Drops
    6.50
     dro
    6.46
    Activations Density 0.007%

    No Known Activations