© 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. 9-ATT-KK
    11. 6488
    Prev
    Next
    INDEX
    Explanations

    elements related to political intrigue and investigations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.08
    1:0.02
    2:0.07
    3:0.06
    4:0.03
    5:0.05
    6:0.07
    7:0.05
    8:0.38
    9:0.08
    10:0.03
    11:0.02
    Negative Logits
    Minnesota
    -4.68
    Ohio
    -4.25
    Baltimore
    -4.13
    Kansas
    -4.08
     Mississ
    -4.08
    Han
    -4.03
     Minnesota
    -4.01
     Bengals
    -3.77
     Maryland
    -3.66
     Timberwolves
    -3.57
    POSITIVE LOGITS
     Argentine
    9.32
     Argentina
    9.03
     Argent
    8.91
     Buenos
    8.35
     Aires
    6.51
     Fernandez
    6.11
     Uruguay
    5.89
     Chilean
    5.86
     Urug
    5.85
     Paragu
    5.77
    Activations Density 0.027%

    No Known Activations