© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 13940
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to performance and measurements

    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
    0:0.12
    1:0.07
    2:0.06
    3:0.10
    4:0.05
    5:0.02
    6:0.05
    7:0.09
    8:0.07
    9:0.04
    10:0.16
    11:0.12
    Negative Logits
     Tuc
    -3.04
    upp
    -2.87
    aux
    -2.80
     Unicorn
    -2.66
    orage
    -2.65
     Oy
    -2.64
     Bucc
    -2.61
    letter
    -2.56
    udeb
    -2.53
    wic
    -2.51
    POSITIVE LOGITS
    ITNESS
    2.88
     Santana
    2.87
     Challenger
    2.83
     Maxim
    2.77
     Gauntlet
    2.71
     —
    2.62
     Emin
    2.60
     Ves
    2.53
     synchronized
    2.52
     podium
    2.48
    Activations Density 0.001%

    No Known Activations