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. 14602
    Prev
    Next
    INDEX
    Explanations

    elements related to crowdfunding and game development

    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
    0:0.12
    1:0.16
    2:0.09
    3:0.03
    4:0.02
    5:0.01
    6:0.11
    7:0.09
    8:0.02
    9:0.03
    10:0.22
    11:0.05
    Negative Logits
     NEO
    -3.01
     Ying
    -2.50
     Bangkok
    -2.41
     Sov
    -2.39
     Tuc
    -2.35
    eret
    -2.32
     Perez
    -2.31
    ouls
    -2.29
     Sut
    -2.28
     Niet
    -2.25
    POSITIVE LOGITS
     Gall
    9.43
    Gall
    8.93
    gall
    7.04
     gall
    6.39
     Gal
    5.11
     Gallagher
    4.90
    Gal
    4.74
    gal
    4.31
     gal
    4.18
     Gard
    3.72
    Activations Density 0.013%

    No Known Activations