© 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. 10-ATT-KK
    11. 10764
    Prev
    Next
    INDEX
    Explanations

    expressions related to retirement decisions in a sports context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.19
    1:0.11
    2:0.06
    3:0.03
    4:0.04
    5:0.03
    6:0.07
    7:0.11
    8:0.02
    9:0.04
    10:0.19
    11:0.04
    Negative Logits
     Budapest
    -3.18
     tel
    -3.15
     JD
    -3.13
    atel
    -3.03
    Hung
    -3.02
     phyl
    -2.86
     Cyan
    -2.84
     SSH
    -2.82
     Taiwanese
    -2.79
     Hung
    -2.71
    POSITIVE LOGITS
     Spur
    9.30
     Pens
    3.64
     spur
    3.64
     Fur
    3.62
    Sp
    3.45
     Spike
    3.40
     Gree
    3.29
     Diesel
    3.21
     Cur
    3.21
     Scor
    3.19
    Activations Density 0.004%

    No Known Activations