© 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. 10-ATT-KK
    11. 9695
    Prev
    Next
    INDEX
    Explanations

    specific player statistics and identifiers in sports-related text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.05
    2:0.17
    3:0.05
    4:0.07
    5:0.03
    6:0.04
    7:0.15
    8:0.05
    9:0.05
    10:0.07
    11:0.14
    Negative Logits
     nutrients
    -2.40
     oats
    -2.28
     partition
    -2.24
     partitions
    -2.23
     renegoti
    -2.22
     Cosmetic
    -2.21
     mates
    -2.19
    orman
    -2.18
     irrig
    -2.17
     pigment
    -2.17
    POSITIVE LOGITS
    HR
    3.33
    CF
    2.94
    HB
    2.90
     CP
    2.71
    SB
    2.69
    OF
    2.67
    retty
    2.65
    RP
    2.64
    DH
    2.64
    ebin
    2.62
    Activations Density 0.001%

    No Known Activations