© 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. 7293
    Prev
    Next
    INDEX
    Explanations

    elements of programming or code-related structures

    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
    0:0.05
    1:0.05
    2:0.06
    3:0.06
    4:0.10
    5:0.19
    6:0.06
    7:0.09
    8:0.06
    9:0.12
    10:0.05
    11:0.05
    Negative Logits
     Mobil
    -2.21
     Frequ
    -2.13
     Nanto
    -2.13
     Butt
    -2.13
     Telesc
    -2.12
    ciating
    -2.05
     Conserv
    -2.05
     Lack
    -2.03
     exhibits
    -1.98
     Regulation
    -1.96
    POSITIVE LOGITS
     :=
    2.88
     <-
    2.78
     print
    2.78
    (_
    2.76
     return
    2.63
     ans
    2.62
    keyes
    2.60
    [[
    2.57
    ({
    2.54
     +=
    2.53
    Activations Density 0.067%

    No Known Activations