© 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. 19441
    Prev
    Next
    INDEX
    Explanations

    key phrases and specific details related to statements and discussions in a report or news article

    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
    0:0.23
    1:0.10
    2:0.08
    3:0.06
    4:0.05
    5:0.02
    6:0.11
    7:0.10
    8:0.03
    9:0.03
    10:0.09
    11:0.05
    Negative Logits
     Sob
    -3.23
     latex
    -3.23
     CLS
    -3.11
     nep
    -3.09
    ktop
    -2.96
     Skinner
    -2.94
     LSD
    -2.88
     treadmill
    -2.85
     Nib
    -2.81
     Audi
    -2.81
    POSITIVE LOGITS
     Cannon
    8.27
     cannon
    6.57
     cannons
    5.54
    annon
    5.07
     artillery
    4.18
     Gunn
    3.76
    Billy
    3.50
     Polaris
    3.46
     GUN
    3.37
     Confederate
    3.32
    Activations Density 0.001%

    No Known Activations