© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 27340
    Prev
    Next
    INDEX
    Explanations

    references to food and meals, particularly those related to preparation and serving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.02
    2:0.06
    3:0.06
    4:0.04
    5:0.04
    6:0.05
    7:0.03
    8:0.05
    9:0.05
    10:0.14
    11:0.36
    Negative Logits
     beverage
    -1.93
     cereal
    -1.92
     sausage
    -1.91
     foods
    -1.88
     pork
    -1.87
    sweet
    -1.85
     flav
    -1.83
    Ingredients
    -1.82
    cake
    -1.81
    food
    -1.81
    POSITIVE LOGITS
     Emin
    1.73
     DPR
    1.58
     Millennium
    1.45
     acceleration
    1.44
    Jr
    1.43
     figure
    1.40
     GPS
    1.37
     powered
    1.34
     scanner
    1.33
     Metatron
    1.32
    Activations Density 0.416%

    No Known Activations