© 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. 7316
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptors related to rarity and commonality in a context

    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
    0:0.04
    1:0.03
    2:0.14
    3:0.06
    4:0.15
    5:0.08
    6:0.05
    7:0.06
    8:0.16
    9:0.10
    10:0.04
    11:0.04
    Negative Logits
    =[
    -3.26
    >[
    -3.06
     =
    -3.02
    =-=-=-=-
    -2.96
    <
    -2.85
    [/
    -2.75
    *:
    -2.73
     [+
    -2.72
    =~
    -2.65
    )</
    -2.62
    POSITIVE LOGITS
     Canaver
    2.99
     96
    2.39
     97
    2.38
     Lent
    2.23
     71
    2.23
     66
    2.20
    percent
    2.15
     veterinary
    2.14
     86
    2.10
     percent
    2.09
    Activations Density 0.002%

    No Known Activations