© 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. 12828
    Prev
    Next
    INDEX
    Explanations

    questions and uncertainty

    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
    0:0.19
    1:0.11
    2:0.06
    3:0.05
    4:0.04
    5:0.02
    6:0.11
    7:0.10
    8:0.03
    9:0.06
    10:0.12
    11:0.05
    Negative Logits
     BM
    -3.38
    ּ
    -3.23
     irrad
    -3.17
    א
    -3.04
     goblin
    -2.98
     Yellowstone
    -2.72
     Warsaw
    -2.71
    Wi
    -2.68
    yrim
    -2.60
    bryce
    -2.57
    POSITIVE LOGITS
     Fernand
    8.87
    ernand
    4.15
     Fernando
    4.00
     Jaguar
    3.73
     Agu
    3.64
     Cout
    3.55
     Hou
    3.50
    inho
    3.48
     Fitz
    3.46
     Ferdinand
    3.43
    Activations Density 0.000%

    No Known Activations