© 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. 10873
    Prev
    Next
    INDEX
    Explanations

    references to legal or political accusations and issues related to corruption

    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
    1:0.06
    2:0.07
    3:0.08
    4:0.05
    5:0.03
    6:0.07
    7:0.08
    8:0.03
    9:0.05
    10:0.17
    11:0.05
    Negative Logits
     Quan
    -3.36
     Fresno
    -3.35
     shark
    -3.24
     Zoro
    -3.23
    CLA
    -3.16
     Earthqu
    -3.03
     Proposition
    -2.98
     Xie
    -2.98
     Pharaoh
    -2.96
     sunscreen
    -2.93
    POSITIVE LOGITS
     Eston
    10.36
     Estonia
    9.79
     Latvia
    6.60
     Baltic
    6.29
     Helsinki
    5.81
     Tall
    5.59
     Lithuania
    5.57
    Balt
    5.47
     Finland
    5.43
     Lithuan
    5.29
    Activations Density 0.009%

    No Known Activations