© 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. 6327
    Prev
    Next
    INDEX
    Explanations

    references to violent incidents or attacks

    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
    0:0.08
    1:0.01
    2:0.09
    3:0.10
    4:0.02
    5:0.06
    6:0.03
    7:0.06
    8:0.43
    9:0.02
    10:0.02
    11:0.02
    Negative Logits
     Wilde
    -4.21
     bunny
    -3.55
     Luigi
    -3.24
     Nether
    -3.21
     Piet
    -3.13
    chester
    -3.11
    witch
    -3.08
     Droid
    -3.06
     HTC
    -3.06
     Vermont
    -3.03
    POSITIVE LOGITS
     Baghdad
    8.56
     Iraqi
    7.95
    Iraq
    7.75
     Iraqis
    7.50
     Mosul
    7.25
     Kurdistan
    6.99
     Saddam
    6.66
     Sunni
    6.50
     Shiite
    6.48
     Kurdish
    6.38
    Activations Density 0.216%

    No Known Activations