© 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. 6729
    Prev
    Next
    INDEX
    Explanations

    financial amounts and related figures

    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
    0:0.07
    1:0.04
    2:0.03
    3:0.12
    4:0.06
    5:0.13
    6:0.15
    7:0.02
    8:0.07
    9:0.10
    10:0.03
    11:0.12
    Negative Logits
     Beard
    -3.75
    Wolf
    -3.27
     Pig
    -3.11
     Egg
    -2.97
    Barn
    -2.96
     Xue
    -2.96
     Wool
    -2.92
    Beast
    -2.84
     Yard
    -2.84
     SUN
    -2.81
    POSITIVE LOGITS
     crore
    4.32
     lakh
    3.32
    cro
    3.06
     cro
    2.97
    ocl
    2.69
    nai
    2.65
    afort
    2.61
     coun
    2.59
     airst
    2.54
    cms
    2.53
    Activations Density 0.002%

    No Known Activations