© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-ATT-KK
    11. 14395
    Prev
    Next
    INDEX
    Explanations

    references to scientific findings and research studies related to health and metabolism

    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
    0:0.20
    1:0.11
    2:0.05
    3:0.11
    4:0.06
    5:0.03
    6:0.06
    7:0.09
    8:0.03
    9:0.04
    10:0.10
    11:0.07
    Negative Logits
     Brus
    -3.76
     Mellon
    -3.65
     Sask
    -3.40
     Tinker
    -3.29
     Avalanche
    -3.22
    Ark
    -3.15
     Chimera
    -3.13
     Tarant
    -3.07
     Bot
    -3.06
     Ot
    -3.04
    POSITIVE LOGITS
     fasting
    7.70
     Ramadan
    5.78
    fast
    4.38
     Judaism
    3.83
     hunger
    3.80
    Muslims
    3.60
     Feast
    3.54
     piety
    3.51
     dh
    3.45
     caloric
    3.43
    Activations Density 0.001%

    No Known Activations