© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 19142
    Prev
    Next
    INDEX
    Explanations

    business-related actions and actors within Chinese commerce and leadership contexts

    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
    0:0.22
    1:0.02
    2:0.11
    3:0.08
    4:0.04
    5:0.08
    6:0.06
    7:0.05
    8:0.17
    9:0.06
    10:0.04
    11:0.02
    Negative Logits
     Cullen
    -3.10
     Goddard
    -2.94
     Lancaster
    -2.93
     Rutherford
    -2.90
     Ulster
    -2.89
     Hitchcock
    -2.88
     Arkham
    -2.85
     Romero
    -2.85
     Temper
    -2.83
     Presbyter
    -2.83
    POSITIVE LOGITS
     Alibaba
    6.91
    ibaba
    4.82
     yuan
    4.40
     Sina
    3.99
     Chinese
    3.94
    Chinese
    3.82
     Zhu
    3.79
     Yuan
    3.63
     Bai
    3.62
     China
    3.55
    Activations Density 0.005%

    No Known Activations