© 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. 17461
    Prev
    Next
    INDEX
    Explanations

    words related to child safety, specifically in digital environments

    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
    1:0.13
    2:0.07
    3:0.05
    4:0.03
    5:0.03
    6:0.19
    7:0.13
    8:0.04
    9:0.04
    10:0.14
    11:0.05
    Negative Logits
    isphere
    -2.74
     cone
    -2.73
     FEC
    -2.69
     cones
    -2.39
     blocker
    -2.34
     controller
    -2.34
    sticks
    -2.33
     selector
    -2.32
    gency
    -2.31
     block
    -2.31
    POSITIVE LOGITS
     Prof
    7.33
    Prof
    6.15
     prof
    4.85
    prof
    4.83
     Professor
    3.94
     professors
    3.60
     professor
    3.49
    Professor
    3.39
     lecturer
    3.36
     Academic
    3.27
    Activations Density 0.008%

    No Known Activations