© 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. 20043
    Prev
    Next
    INDEX
    Explanations

    concepts related to economic systems, particularly involving value creation and business strategy

    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
    0:0.03
    1:0.06
    2:0.03
    3:0.18
    4:0.03
    5:0.08
    6:0.03
    7:0.32
    8:0.05
    9:0.01
    10:0.08
    11:0.03
    Negative Logits
    terness
    -2.37
    ffen
    -2.29
    ngth
    -2.27
    idential
    -2.22
    agos
    -2.21
    incial
    -1.98
    bian
    -1.98
    uine
    -1.97
    stood
    -1.95
    aic
    -1.95
    POSITIVE LOGITS
     Fukushima
    2.45
    ================================================================
    2.34
     =================================
    2.04
     Chromebook
    2.03
     Starg
    2.01
     Kepler
    1.97
    ------------------------------------------------
    1.93
     certs
    1.92
     Mord
    1.92
     Starcraft
    1.88
    Activations Density 0.092%

    No Known Activations