© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 30145
    Prev
    Next
    INDEX
    Explanations

    references to statistical metrics or achievements in sports

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.08
    1:0.10
    2:0.08
    3:0.08
    4:0.07
    5:0.07
    6:0.07
    7:0.07
    8:0.09
    9:0.10
    10:0.07
    11:0.08
    Negative Logits
     Shades
    -1.87
     Akin
    -1.82
     Seasons
    -1.78
     Hus
    -1.75
     Diesel
    -1.68
     Bans
    -1.67
    aughs
    -1.67
     Simmons
    -1.66
    Bey
    -1.63
     Singer
    -1.63
    POSITIVE LOGITS
    icter
    1.88
    buquerque
    1.84
    integer
    1.80
    endum
    1.72
     cryst
    1.66
     chronological
    1.66
    commun
    1.65
     incor
    1.64
    central
    1.63
    conservancy
    1.63
    Activations Density 0.000%

    No Known Activations