© 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. 20409
    Prev
    Next
    INDEX
    Explanations

    elements related to promotion and marketing strategies

    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
    0:0.06
    1:0.02
    2:0.05
    3:0.25
    4:0.02
    5:0.10
    6:0.03
    7:0.05
    8:0.03
    9:0.02
    10:0.31
    11:0.02
    Negative Logits
     blinked
    -2.51
     obliged
    -2.42
    stretched
    -2.15
    eded
    -2.14
     shuff
    -2.07
     booted
    -2.06
     rushed
    -2.04
     dragged
    -2.02
     stepped
    -1.94
     stumbling
    -1.93
    POSITIVE LOGITS
     advoc
    2.29
     lifestyle
    2.21
     livest
    2.18
     lifestyles
    2.17
     wellness
    2.09
     hobbies
    2.03
    Downloadha
    1.95
     Positive
    1.95
     behavi
    1.94
     realism
    1.94
    Activations Density 0.030%

    No Known Activations