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. 14628
    Prev
    Next
    INDEX
    Explanations

    conjunctions and coordinating phrases that connect ideas

    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
    0:0.07
    1:0.02
    2:0.02
    3:0.12
    4:0.23
    5:0.02
    6:0.04
    7:0.17
    8:0.02
    9:0.03
    10:0.06
    11:0.14
    Negative Logits
    ijing
    -3.16
     Beijing
    -3.10
     PLA
    -2.94
     Chinese
    -2.92
    Chinese
    -2.85
     Chinatown
    -2.74
     ILCS
    -2.63
     Mandarin
    -2.56
    Xi
    -2.46
    ��
    -2.39
    POSITIVE LOGITS
     Norway
    2.88
     Monteneg
    2.85
     Netherlands
    2.72
     Serbia
    2.70
     Berm
    2.57
     Maurit
    2.57
    Mor
    2.54
    ―
    2.54
     Kaz
    2.47
     Scand
    2.46
    Activations Density 0.036%

    No Known Activations