© 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. 6989
    Prev
    Next
    INDEX
    Explanations

    culinary ingredients and quantities

    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
    0:0.12
    1:0.03
    2:0.04
    3:0.09
    4:0.20
    5:0.04
    6:0.04
    7:0.14
    8:0.08
    9:0.06
    10:0.04
    11:0.06
    Negative Logits
    enegger
    -2.43
     malware
    -2.39
    seless
    -2.39
     piracy
    -2.28
    trap
    -2.27
    repair
    -2.21
    ł
    -2.20
     toilets
    -2.15
     bandits
    -2.15
     artifacts
    -2.09
    POSITIVE LOGITS
     tbsp
    2.56
     softened
    2.51
     diced
    2.50
     whipped
    2.34
     chopped
    2.33
     tsp
    2.33
     Stev
    2.29
    fine
    2.25
     oz
    2.19
     Veg
    2.16
    Activations Density 0.031%

    No Known Activations