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. 9-ATT-KK
    6. 7668
    Prev
    Next
    INDEX
    Explanations

    the phrase "of" indicating relationships or ownership

    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
    1:0.09
    2:0.07
    3:0.08
    4:0.08
    5:0.07
    6:0.07
    7:0.07
    8:0.09
    9:0.08
    10:0.07
    11:0.09
    Negative Logits
    ulhu
    -2.72
     fortun
    -2.67
    $$$$
    -2.62
    states
    -2.54
     civilizations
    -2.47
    ��
    -2.45
    Sov
    -2.44
     Sorce
    -2.42
     Carth
    -2.41
     Chinatown
    -2.28
    POSITIVE LOGITS
     ­
    2.83
     �
    2.70
     SNAP
    2.51
    ordinary
    2.48
    ————
    2.47
     Labrador
    2.43
    tackle
    2.40
     Archie
    2.37
    rieve
    2.34
    illin
    2.34
    Activations Density 0.000%

    No Known Activations