© 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. 541
    Prev
    Next
    INDEX
    Explanations

    references to trade and economic topics

    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
    0:0.07
    1:0.03
    2:0.10
    3:0.04
    4:0.04
    5:0.04
    6:0.29
    7:0.03
    8:0.04
    9:0.22
    10:0.02
    11:0.03
    Negative Logits
     erection
    -3.87
     Hollow
    -3.56
    ヴァ
    -3.48
    Param
    -3.36
     batteries
    -3.36
     HELL
    -3.35
    Nev
    -3.34
     Alam
    -3.22
     Eps
    -3.20
     Heaven
    -3.19
    POSITIVE LOGITS
     Trade
    9.36
    trade
    8.89
    Trade
    8.47
     trade
    8.32
     trades
    7.22
     trading
    6.27
     Trader
    6.24
     traded
    6.20
     traders
    6.16
     trader
    6.15
    Activations Density 0.018%

    No Known Activations