© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 24185
    Prev
    Next
    INDEX
    Explanations

    references to sports statistics and historical performance

    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
    1:0.04
    2:0.04
    3:0.19
    4:0.03
    5:0.07
    6:0.03
    7:0.11
    8:0.05
    9:0.02
    10:0.29
    11:0.04
    Negative Logits
    eday
    -1.92
     directions
    -1.86
     voic
    -1.84
    ocations
    -1.80
    phas
    -1.74
    soDeliveryDate
    -1.73
    KNOWN
    -1.68
     Tomorrow
    -1.67
    positive
    -1.67
    acular
    -1.66
    POSITIVE LOGITS
     1981
    3.21
     1979
    3.19
     2001
    3.11
     1973
    3.11
     1997
    3.07
     1998
    3.02
     1982
    3.02
     1977
    3.01
     1999
    2.99
     1986
    2.97
    Activations Density 0.033%

    No Known Activations