© 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. 8563
    Prev
    Next
    INDEX
    Explanations

    indications of significant visual evidence or demonstrations

    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
    1:0.08
    2:0.11
    3:0.11
    4:0.07
    5:0.03
    6:0.07
    7:0.07
    8:0.05
    9:0.03
    10:0.09
    11:0.12
    Negative Logits
    ��
    -2.95
     allele
    -2.66
    angan
    -2.57
     Labrador
    -2.56
    Jenn
    -2.52
    termination
    -2.51
     variance
    -2.51
     Klu
    -2.50
     nep
    -2.46
     variability
    -2.46
    POSITIVE LOGITS
     Pictures
    4.04
    OTOS
    3.87
     PH
    3.45
     Photos
    3.42
     Phot
    3.39
     Awards
    3.37
     Flowers
    3.36
     Oscars
    3.29
    Photos
    3.07
     Picks
    3.04
    Activations Density 0.000%

    No Known Activations