© 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. 17317
    Prev
    Next
    INDEX
    Explanations

    events related to accidents and their implications

    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
    0:0.21
    1:0.08
    2:0.05
    3:0.06
    4:0.09
    5:0.03
    6:0.09
    7:0.10
    8:0.02
    9:0.06
    10:0.10
    11:0.07
    Negative Logits
     Benghazi
    -4.02
     Libya
    -3.63
     Moj
    -3.48
     Tripoli
    -3.36
     Jamal
    -3.36
     Xie
    -3.32
     Morsi
    -3.24
     Gujar
    -3.17
     Patel
    -3.16
     Gaddafi
    -3.11
    POSITIVE LOGITS
     Freud
    8.19
     psycho
    5.77
     Psycho
    5.01
     psychiatrists
    4.77
    Psych
    4.68
     Psych
    4.64
     psych
    4.59
     Psychiat
    4.51
     psychiatrist
    4.50
    Fre
    4.47
    Activations Density 0.001%

    No Known Activations