© 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. 13378
    Prev
    Next
    INDEX
    Explanations

    references to expert commentary or analysis regarding events or situations

    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
    0:0.18
    1:0.11
    2:0.08
    3:0.05
    4:0.02
    5:0.02
    6:0.12
    7:0.08
    8:0.02
    9:0.04
    10:0.17
    11:0.04
    Negative Logits
     Vampire
    -3.33
     Compan
    -3.15
     dd
    -3.15
    ignt
    -3.10
    bats
    -3.10
     Houth
    -3.09
     concess
    -3.05
     Ans
    -3.04
     Xue
    -3.01
    agall
    -2.98
    POSITIVE LOGITS
     Kerr
    10.57
     KD
    4.48
     Curry
    4.39
     Rutherford
    4.33
     Warriors
    4.32
    asketball
    4.06
     McGr
    4.01
     Kelvin
    3.92
     Kr
    3.89
     Kahn
    3.83
    Activations Density 0.000%

    No Known Activations