© 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. 6642
    Prev
    Next
    INDEX
    Explanations

    phrases related to illegal activities or law enforcement matters

    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
    0:0.06
    1:0.09
    2:0.04
    3:0.03
    4:0.04
    5:0.03
    6:0.04
    7:0.39
    8:0.03
    9:0.04
    10:0.11
    11:0.06
    Negative Logits
    trap
    -2.63
    ulk
    -2.52
     lith
    -2.48
     Traps
    -2.47
     scen
    -2.39
    steam
    -2.37
     Sterling
    -2.35
    Sham
    -2.35
     slopes
    -2.35
    istar
    -2.33
    POSITIVE LOGITS
    ��
    3.14
     Nare
    2.77
     dissertation
    2.38
    Gene
    2.33
     Darwin
    2.32
     prescription
    2.29
    IBLE
    2.22
     exams
    2.22
     exam
    2.20
     Patent
    2.16
    Activations Density 0.003%

    No Known Activations