© 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. 12360
    Prev
    Next
    INDEX
    Explanations

    elements related to sports statistics and player details

    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
    0:0.05
    1:0.03
    2:0.11
    3:0.09
    4:0.03
    5:0.06
    6:0.04
    7:0.08
    8:0.31
    9:0.04
    10:0.06
    11:0.04
    Negative Logits
    Assad
    -3.21
     Browns
    -3.13
     Baal
    -2.93
     Allaah
    -2.91
     Sinn
    -2.89
    paio
    -2.83
     Homs
    -2.76
    arse
    -2.74
    estate
    -2.73
    alos
    -2.72
    POSITIVE LOGITS
     NW
    4.00
     Reign
    3.67
     Abby
    3.49
    WA
    3.19
     Wand
    3.00
     Glory
    2.98
     Kane
    2.97
    NW
    2.97
     Sweden
    2.90
     Anders
    2.86
    Activations Density 0.006%

    No Known Activations