© 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. 22850
    Prev
    Next
    INDEX
    Explanations

    terms relating to food safety and packaging, specifically focusing on canned foods and their potential hazards

    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
    0:0.24
    1:0.05
    2:0.08
    3:0.06
    4:0.05
    5:0.02
    6:0.05
    7:0.15
    8:0.03
    9:0.04
    10:0.12
    11:0.07
    Negative Logits
    Beck
    -3.66
     Beck
    -3.60
     Feld
    -3.46
    ―
    -3.29
     Camel
    -3.12
     Astral
    -2.98
     FX
    -2.97
     Athe
    -2.95
     Fey
    -2.86
     Planes
    -2.78
    POSITIVE LOGITS
     tomatoes
    6.76
     tomato
    6.64
     Tomato
    6.09
     peppers
    4.88
     tomat
    4.54
     cuc
    4.04
    atoes
    3.92
     vegetables
    3.84
     basil
    3.71
     lettuce
    3.67
    Activations Density 0.002%

    No Known Activations