Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14673
    Prev
    Next
    INDEX
    Explanations

    patterns of consumer preferences and evaluations in relation to whiskey or bourbon

    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
    1:0.04
    2:0.06
    3:0.05
    4:0.05
    5:0.04
    6:0.06
    7:0.20
    8:0.02
    9:0.04
    10:0.08
    11:0.06
    Negative Logits
    Pokémon
    -3.88
     Pokémon
    -3.67
     Pikachu
    -3.58
     Emerald
    -3.29
     Poké
    -3.29
     Tacoma
    -3.25
    Seattle
    -3.23
     Orb
    -3.18
     Pearce
    -3.15
    oké
    -2.99
    POSITIVE LOGITS
     Bourbon
    4.94
     bourbon
    4.77
     bour
    3.73
    lycer
    3.38
     Whis
    3.08
     whiskey
    3.02
     Rye
    3.01
     rye
    2.95
     whis
    2.93
    pire
    2.79
    Activations Density 0.003%

    No Known Activations