© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 19657
    Prev
    Next
    INDEX
    Explanations

    phrases related to architectural design and development projects

    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
    0:0.15
    1:0.03
    2:0.14
    3:0.12
    4:0.05
    5:0.10
    6:0.06
    7:0.07
    8:0.07
    9:0.05
    10:0.05
    11:0.04
    Negative Logits
     architectural
    -3.23
     decorative
    -3.13
     aesthetic
    -3.11
     art
    -3.08
     artistic
    -3.03
     beaut
    -2.96
     aesthetics
    -2.96
     architecture
    -2.96
     artwork
    -2.94
     artisan
    -2.85
    POSITIVE LOGITS
    Republicans
    2.77
     Gingrich
    2.75
     Huckabee
    2.67
     Santorum
    2.67
     Petraeus
    2.64
     Limbaugh
    2.63
     McCain
    2.62
    Republican
    2.60
    ghazi
    2.59
    anamo
    2.57
    Activations Density 0.003%

    No Known Activations