© 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. 13178
    Prev
    Next
    INDEX
    Explanations

    references to historical dates and events

    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
    •Greater Than Circuit
    Historical dates and events

    No Comments

    Head Attr Weights
    0:0.20
    1:0.08
    2:0.13
    3:0.07
    4:0.04
    5:0.02
    6:0.04
    7:0.20
    8:0.02
    9:0.05
    10:0.07
    11:0.03
    Negative Logits
    Sov
    -3.34
     Hezbollah
    -2.86
     rocket
    -2.67
     McDonnell
    -2.54
    ć
    -2.54
     rockets
    -2.48
     Airbus
    -2.47
    ------------------------------------------------
    -2.46
    avi
    -2.46
     Aman
    -2.44
    POSITIVE LOGITS
     1890
    3.74
     1870
    3.61
     1896
    3.55
     1880
    3.50
     1901
    3.45
     1895
    3.42
     1904
    3.31
     1899
    3.31
     1898
    3.25
     1905
    3.25
    Activations Density 0.030%

    No Known Activations