© 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. 9-ATT-KK
    11. 6827
    Prev
    Next
    INDEX
    Explanations

    instances of interactions or references between individuals and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.02
    2:0.03
    3:0.04
    4:0.06
    5:0.03
    6:0.12
    7:0.02
    8:0.03
    9:0.51
    10:0.02
    11:0.02
    Negative Logits
    я
    -3.50
    gio
    -3.38
     Hawkins
    -3.29
    gan
    -3.22
    ician
    -3.14
    gans
    -3.13
     McCann
    -3.07
     Griffin
    -3.06
     Krishna
    -3.01
    anes
    -3.00
    POSITIVE LOGITS
    TT
    5.93
    T
    5.78
     T
    5.76
     TA
    5.74
    Ts
    5.70
     Tat
    5.66
     TT
    5.63
     Tucker
    5.54
     Tet
    5.31
     TJ
    5.27
    Activations Density 0.394%

    No Known Activations