© 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. 5698
    Prev
    Next
    INDEX
    Explanations

    instances of people being harmed or injured in various contexts

    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
    0:0.06
    1:0.03
    2:0.22
    3:0.10
    4:0.07
    5:0.18
    6:0.03
    7:0.07
    8:0.06
    9:0.02
    10:0.06
    11:0.03
    Negative Logits
     envy
    -1.99
     Oprah
    -1.93
     Babe
    -1.86
    osterone
    -1.85
     someday
    -1.79
     doping
    -1.72
    uct
    -1.69
     Papers
    -1.68
     Bonds
    -1.68
     recept
    -1.67
    POSITIVE LOGITS
     civilians
    2.29
    ��
    2.14
    irens
    2.07
     casualties
    2.07
     gunfire
    2.04
     ranged
    2.01
     gunmen
    2.00
     wounded
    1.99
    ��
    1.99
     civilian
    1.97
    Activations Density 0.131%

    No Known Activations