© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 23189
    Prev
    Next
    INDEX
    Explanations

    phrases related to gut health and its impact on overall well-being

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.26
    1:0.05
    2:0.05
    3:0.05
    4:0.09
    5:0.02
    6:0.06
    7:0.12
    8:0.02
    9:0.04
    10:0.11
    11:0.09
    Negative Logits
    Tesla
    -3.55
     Tesla
    -3.50
     Dmit
    -3.45
     bitcoin
    -3.42
     BMW
    -3.41
    vard
    -3.39
     Drone
    -3.35
     Mustang
    -3.34
     Kry
    -3.28
     Pavel
    -3.18
    POSITIVE LOGITS
     intestinal
    6.61
    estinal
    6.33
     intestine
    5.67
     muc
    5.36
     GI
    5.28
     bowel
    5.14
     Gut
    5.00
     gastro
    4.94
     gastrointestinal
    4.94
     fec
    4.77
    Activations Density 0.021%

    No Known Activations