© 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. 12087
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues and public policy

    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
    0:0.01
    1:0.01
    2:0.04
    3:0.03
    4:0.03
    5:0.65
    6:0.01
    7:0.02
    8:0.01
    9:0.10
    10:0.01
    11:0.02
    Negative Logits
     Powered
    -2.79
    escap
    -2.75
     Lakes
    -2.75
    again
    -2.72
    Anyone
    -2.63
    (){
    -2.60
     anybody
    -2.59
    Article
    -2.56
     Glover
    -2.52
     insepar
    -2.48
    POSITIVE LOGITS
     than
    12.29
    than
    11.46
     Than
    9.10
     compared
    5.50
     rather
    4.38
     TH
    3.84
    rather
    3.62
     then
    3.62
     fewer
    3.53
    soDeliveryDate
    3.52
    Activations Density 0.887%

    No Known Activations