© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10052
    Prev
    Next
    INDEX
    Explanations

    references to specific times, events, or places in relation to solar eclipses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.03
    2:0.06
    3:0.04
    4:0.05
    5:0.05
    6:0.19
    7:0.06
    8:0.14
    9:0.18
    10:0.03
    11:0.03
    Negative Logits
    acebook
    -3.82
    Pitt
    -3.79
    ollah
    -3.68
     Patt
    -3.67
     Steelers
    -3.62
     Franch
    -3.59
     Pittsburgh
    -3.52
     Pats
    -3.50
     vodka
    -3.44
     MSG
    -3.40
    POSITIVE LOGITS
     Eclipse
    9.85
     eclipse
    7.92
    clipse
    7.48
     Jasper
    4.77
     eclips
    4.63
     Java
    4.17
     Moon
    4.11
     Jade
    3.99
     Solar
    3.95
     Exodus
    3.94
    Activations Density 0.001%

    No Known Activations