© 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. 23214
    Prev
    Next
    INDEX
    Explanations

    financial terms and references related to Bitcoin and investment strategies

    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
    0:0.20
    1:0.08
    2:0.11
    3:0.06
    4:0.03
    5:0.02
    6:0.07
    7:0.09
    8:0.03
    9:0.04
    10:0.18
    11:0.04
    Negative Logits
     Hammond
    -3.59
     Bristol
    -3.35
     slab
    -2.97
    slice
    -2.86
     Weston
    -2.81
     Creed
    -2.77
     Glover
    -2.77
     Sloan
    -2.75
     Nebraska
    -2.75
    Ham
    -2.74
    POSITIVE LOGITS
     Yu
    9.11
    Yu
    8.91
     Ryu
    5.11
    yu
    5.08
     Tsu
    5.03
     Xu
    4.95
     Chu
    4.76
     Pu
    4.71
     Zhu
    4.62
     pu
    4.45
    Activations Density 0.003%

    No Known Activations