© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 12009
    Prev
    Next
    INDEX
    Explanations

    references to literature, authors, and significant cultural impacts in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.03
    3:0.04
    4:0.14
    5:0.38
    6:0.02
    7:0.03
    8:0.05
    9:0.12
    10:0.02
    11:0.09
    Negative Logits
    ):
    -4.26
    ]:
    -4.21
    .):
    -4.10
    :]
    -3.97
    :-
    -3.84
     :
    -3.30
    :[
    -3.20
    :"
    -3.13
    :(
    -2.99
    :
    -2.90
    POSITIVE LOGITS
     Travels
    3.11
     Unle
    3.04
     examines
    2.94
     Begins
    2.73
     Versus
    2.73
    "},"
    2.72
     explores
    2.68
     Gets
    2.63
    then
    2.63
     Increases
    2.63
    Activations Density 0.073%

    No Known Activations