© 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. 11883
    Prev
    Next
    INDEX
    Explanations

    references to vehicle accidents and crashes

    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
    2:0.03
    3:0.08
    4:0.14
    5:0.03
    6:0.07
    7:0.13
    8:0.02
    9:0.06
    10:0.06
    11:0.07
    Negative Logits
     polygamy
    -2.80
    ormons
    -2.62
     Uganda
    -2.61
    eret
    -2.55
     quotas
    -2.48
     Mormons
    -2.47
     Ug
    -2.45
     fulfillment
    -2.40
    arte
    -2.38
     stocking
    -2.38
    POSITIVE LOGITS
     crash
    5.90
    Crash
    5.72
     crashes
    5.55
     Crash
    4.99
     wreckage
    4.85
     crashed
    4.76
     accident
    4.75
     collision
    4.53
     wreck
    4.36
     crashing
    4.33
    Activations Density 0.159%

    No Known Activations