© 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. 10461
    Prev
    Next
    INDEX
    Explanations

    expressions related to financial transactions and insurance services

    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
    0:0.13
    1:0.05
    2:0.07
    3:0.03
    4:0.05
    5:0.02
    6:0.20
    7:0.15
    8:0.04
    9:0.03
    10:0.12
    11:0.06
    Negative Logits
    atche
    -3.05
     Yosemite
    -2.71
     LT
    -2.53
     Huff
    -2.48
     Lem
    -2.44
     Alban
    -2.42
     NCT
    -2.39
    igious
    -2.32
     Pat
    -2.29
     imag
    -2.28
    POSITIVE LOGITS
     broker
    6.96
     brokers
    6.24
     brokerage
    5.60
     traders
    4.00
     trader
    3.77
     mediation
    3.47
     trading
    3.41
     Bro
    3.41
     trades
    3.30
     Banking
    3.12
    Activations Density 0.002%

    No Known Activations