© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1613
    Prev
    Next
    INDEX
    Explanations

    references to statistical analysis or numerical data in research articles

    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
    0:0.23
    1:0.02
    2:0.03
    3:0.05
    4:0.12
    5:0.11
    6:0.02
    7:0.09
    8:0.04
    9:0.02
    10:0.19
    11:0.03
    Negative Logits
     diplomacy
    -2.17
     civilization
    -1.98
     Conquest
    -1.93
     Civilization
    -1.92
     Emin
    -1.87
    gress
    -1.86
     civilizations
    -1.81
    iHUD
    -1.78
     Vigil
    -1.76
     Train
    -1.76
    POSITIVE LOGITS
     Skydragon
    2.35
    BILITY
    2.19
    apo
    2.17
    SEE
    2.17
    goo
    2.13
    doi
    2.08
     Springer
    2.04
    bsite
    2.03
    viation
    2.00
     photoc
    2.00
    Activations Density 0.002%

    No Known Activations