© 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. 10626
    Prev
    Next
    INDEX
    Explanations

    references to historical events and figures related to civil rights and voting issues

    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
    0:0.23
    1:0.04
    2:0.04
    3:0.05
    4:0.05
    5:0.02
    6:0.15
    7:0.13
    8:0.02
    9:0.06
    10:0.10
    11:0.05
    Negative Logits
     Boulder
    -3.58
     Toad
    -3.48
     Nicarag
    -3.46
     Weld
    -3.44
     Dartmouth
    -3.31
     Erie
    -3.31
     Bender
    -3.29
     opium
    -3.22
     Calais
    -3.20
     Ames
    -3.10
    POSITIVE LOGITS
    TIT
    3.29
     Title
    3.20
     RX
    2.86
    cod
    2.70
     Hawks
    2.63
    Rating
    2.57
     parity
    2.57
     Blu
    2.55
    equal
    2.55
     Sergey
    2.55
    Activations Density 0.000%

    No Known Activations