© 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. 23630
    Prev
    Next
    INDEX
    Explanations

    positive affirmations and descriptions related to culinary skills and experiences

    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
    0:0.33
    1:0.02
    2:0.15
    3:0.07
    4:0.02
    5:0.09
    6:0.04
    7:0.06
    8:0.08
    9:0.02
    10:0.03
    11:0.04
    Negative Logits
     Bonds
    -2.79
     Defender
    -2.59
     Vanguard
    -2.50
     Amnesty
    -2.46
     blockers
    -2.45
     Pall
    -2.42
     ACLU
    -2.38
     Gallup
    -2.35
     outwe
    -2.34
     Springer
    -2.34
    POSITIVE LOGITS
     cook
    5.44
     Recipes
    5.31
     chefs
    5.22
     cooks
    5.18
     Chef
    5.18
     chef
    5.16
     cooking
    5.12
     recipes
    5.09
     Cooking
    4.98
     kitchens
    4.91
    Activations Density 0.119%

    No Known Activations