© 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. 15845
    Prev
    Next
    INDEX
    Explanations

    references to arbitration processes and their implications

    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
    0:0.15
    1:0.02
    2:0.20
    3:0.06
    4:0.03
    5:0.12
    6:0.08
    7:0.03
    8:0.13
    9:0.07
    10:0.04
    11:0.02
    Negative Logits
     Elm
    -3.00
     Mansion
    -2.84
     Eisenhower
    -2.74
     Mul
    -2.74
     Pumpkin
    -2.71
     Cemetery
    -2.71
    alloween
    -2.70
     Klux
    -2.67
    incinn
    -2.66
     Romanian
    -2.63
    POSITIVE LOGITS
     arbitration
    7.19
     arbit
    5.93
     Arbit
    5.39
     tribunal
    4.08
     mediation
    3.92
     dispute
    3.49
     disputes
    3.31
     settlement
    3.29
     Tribunal
    3.25
     clauses
    3.23
    Activations Density 0.003%

    No Known Activations