© 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. 10-ATT-KK
    11. 8471
    Prev
    Next
    INDEX
    Explanations

    references to authoritative figures or essential roles within a context

    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
    0:0.17
    1:0.05
    2:0.05
    3:0.07
    4:0.07
    5:0.05
    6:0.11
    7:0.07
    8:0.05
    9:0.06
    10:0.11
    11:0.08
    Negative Logits
     Watkins
    -3.25
    Gh
    -3.24
     Rider
    -2.93
     Valerie
    -2.88
     Relief
    -2.83
     Rez
    -2.81
     Morsi
    -2.80
     Cairo
    -2.77
    HCR
    -2.71
     gh
    -2.70
    POSITIVE LOGITS
     plank
    6.44
     Pik
    3.61
     biomass
    3.49
     Sponge
    3.47
     marine
    3.43
     ocean
    3.32
     fisheries
    3.31
    acteria
    3.29
     stocking
    3.28
     algae
    3.28
    Activations Density 0.000%

    No Known Activations