© 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. 23040
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or events

    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
    1:0.21
    2:0.03
    3:0.03
    4:0.02
    5:0.03
    6:0.05
    7:0.10
    8:0.04
    9:0.04
    10:0.11
    11:0.05
    Negative Logits
     Tanner
    -3.25
     Till
    -3.12
     Scand
    -3.00
     Cust
    -2.77
    ymm
    -2.76
     Gillespie
    -2.76
     Charlottesville
    -2.72
     Flan
    -2.65
    Alt
    -2.62
     Chill
    -2.58
    POSITIVE LOGITS
    iro
    5.81
    enegger
    3.91
     Moto
    3.42
     Roche
    3.24
    rio
    3.14
     IR
    3.13
     Hiro
    3.05
    Rub
    3.01
    ierrez
    2.98
     Oro
    2.95
    Activations Density 0.001%

    No Known Activations