© 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. 23236
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal processes and judicial authority

    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
    0:0.09
    1:0.03
    2:0.05
    3:0.04
    4:0.04
    5:0.03
    6:0.27
    7:0.03
    8:0.09
    9:0.22
    10:0.03
    11:0.02
    Negative Logits
    thumbnails
    -4.59
     Lawson
    -4.31
    ques
    -4.02
     bell
    -3.53
    merce
    -3.46
     pies
    -3.43
     Monroe
    -3.41
     Dudley
    -3.38
     Lyon
    -3.36
     Puzzles
    -3.33
    POSITIVE LOGITS
     Af
    9.01
    Af
    8.45
    AF
    7.75
     AF
    7.25
    af
    5.76
     af
    5.69
     Alf
    5.34
     Afric
    5.17
     Ethiop
    4.79
     ACE
    4.74
    Activations Density 0.003%

    No Known Activations