© 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. 19566
    Prev
    Next
    INDEX
    Explanations

    numerical data and relationships in the context of financial and corporate topics

    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
    0:0.11
    1:0.10
    2:0.07
    3:0.07
    4:0.05
    5:0.02
    6:0.18
    7:0.09
    8:0.03
    9:0.04
    10:0.11
    11:0.08
    Negative Logits
     Rohing
    -2.72
     Kinn
    -2.61
    usra
    -2.61
    oln
    -2.60
     amph
    -2.59
    odi
    -2.59
     Hodg
    -2.59
    liam
    -2.56
     Owen
    -2.55
     Hod
    -2.53
    POSITIVE LOGITS
     Fortune
    7.36
    fortune
    6.06
     fortune
    4.34
     Tycoon
    3.94
    DAQ
    3.85
     Forbes
    3.76
     CEOs
    3.54
    Oracle
    3.34
    CEO
    3.29
     Entreprene
    3.27
    Activations Density 0.000%

    No Known Activations