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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14708
    Prev
    Next
    INDEX
    Explanations

    sentence endings and punctuation marks

    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
    0:0.27
    1:0.10
    2:0.06
    3:0.04
    4:0.03
    5:0.02
    6:0.10
    7:0.08
    8:0.03
    9:0.04
    10:0.12
    11:0.05
    Negative Logits
    Bell
    -3.54
     Sailor
    -3.45
    romeda
    -3.41
     Telecommunications
    -3.32
     Leviathan
    -3.25
     Oz
    -3.11
     Nept
    -3.05
     iodine
    -3.05
     ot
    -3.04
     Eps
    -2.99
    POSITIVE LOGITS
     Frazier
    10.28
     Fraz
    4.42
     Maul
    3.98
     Frie
    3.77
     Fritz
    3.72
     Kaufman
    3.68
     Fur
    3.67
     Zucker
    3.59
     Fischer
    3.50
     Fowler
    3.49
    Activations Density 0.001%

    No Known Activations