© 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. 21230
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to pricing and trade negotiations

    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
    1:0.02
    2:0.13
    3:0.06
    4:0.04
    5:0.08
    6:0.17
    7:0.04
    8:0.06
    9:0.13
    10:0.03
    11:0.03
    Negative Logits
     Gamb
    -3.23
     Varg
    -3.12
    ̶
    -3.09
    gdala
    -3.06
     Bundle
    -3.03
     Drugs
    -2.95
     voucher
    -2.94
    覚醒
    -2.93
        
    -2.93
     Gum
    -2.92
    POSITIVE LOGITS
    Steel
    7.66
     steel
    7.50
    steel
    7.45
     Steel
    7.45
     weld
    5.03
     corrosion
    4.80
     iron
    4.41
     welding
    4.34
     stainless
    4.26
     corro
    4.13
    Activations Density 0.003%

    No Known Activations