© 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. 17089
    Prev
    Next
    INDEX
    Explanations

    phrases and terminology related to contracts and contractual agreements

    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
    1:0.05
    2:0.12
    3:0.04
    4:0.04
    5:0.07
    6:0.24
    7:0.02
    8:0.05
    9:0.19
    10:0.02
    11:0.03
    Negative Logits
     volcan
    -3.85
     Manson
    -3.75
    mount
    -3.67
     Lauder
    -3.52
     ash
    -3.50
    ugen
    -3.49
     Pale
    -3.45
     Dayton
    -3.45
    enegger
    -3.41
     psychosis
    -3.39
    POSITIVE LOGITS
     Contract
    7.80
     contract
    7.62
    contract
    7.47
     contracts
    7.36
    Contract
    7.10
     contractor
    6.94
     Contracts
    6.88
     contracting
    6.66
     contractors
    6.20
     contracted
    5.93
    Activations Density 0.013%

    No Known Activations