© 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. 2113
    Prev
    Next
    INDEX
    Explanations

    keywords related to statistics and performance metrics

    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
    0:0.10
    1:0.04
    2:0.08
    3:0.05
    4:0.05
    5:0.04
    6:0.20
    7:0.04
    8:0.04
    9:0.24
    10:0.03
    11:0.03
    Negative Logits
     Heller
    -3.87
     Seeds
    -3.62
     Hung
    -3.61
    Hung
    -3.50
     Hungry
    -3.38
     germ
    -3.32
     caves
    -3.31
     Graham
    -3.29
     1911
    -3.27
     Hazel
    -3.22
    POSITIVE LOGITS
     Perform
    6.00
    Performance
    5.90
     Performance
    5.47
    performance
    5.41
     perform
    5.34
     performance
    5.03
     performing
    5.02
     performed
    5.01
     performer
    4.91
     performs
    4.90
    Activations Density 0.003%

    No Known Activations