© 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. 9-ATT-KK
    11. 6358
    Prev
    Next
    INDEX
    Explanations

    the mention of specific entities or brands associated with food and beverages

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.10
    1:0.06
    2:0.07
    3:0.09
    4:0.07
    5:0.06
    6:0.14
    7:0.06
    8:0.07
    9:0.12
    10:0.04
    11:0.06
    Negative Logits
    Pri
    -2.81
     Yor
    -2.60
     pri
    -2.56
    arov
    -2.55
    icer
    -2.49
     escal
    -2.49
     pal
    -2.48
     Chr
    -2.42
    ota
    -2.42
    estamp
    -2.39
    POSITIVE LOGITS
    Mos
    2.85
     Honey
    2.73
     Goose
    2.73
     mosquitoes
    2.69
     Starship
    2.68
     Kund
    2.62
     Goodbye
    2.59
    bugs
    2.56
     Surveillance
    2.52
     Monstrous
    2.51
    Activations Density 0.000%

    No Known Activations