© 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. 10712
    Prev
    Next
    INDEX
    Explanations

    terms related to illegal activities involving drugs, guns, and organized crime

    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
    0:0.03
    1:0.05
    2:0.03
    3:0.04
    4:0.04
    5:0.16
    6:0.03
    7:0.05
    8:0.03
    9:0.42
    10:0.02
    11:0.06
    Negative Logits
     negotiation
    -2.45
    iquette
    -2.44
    checking
    -2.39
     vetting
    -2.35
    iferation
    -2.34
     reckoning
    -2.32
    terness
    -2.29
     pacing
    -2.27
    thening
    -2.27
     narrowing
    -2.26
    POSITIVE LOGITS
     spheres
    2.15
    urized
    2.10
     capsules
    2.09
     sculptures
    2.07
     cans
    2.07
     outdoors
    2.06
     jars
    2.05
    inous
    2.05
     specimens
    2.04
     pods
    2.03
    Activations Density 0.576%

    No Known Activations