© 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. 2-ATT-KK
    11. 11525
    Prev
    Next
    INDEX
    Explanations

    references to military conflicts and airstrikes

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.04
    1:0.13
    2:0.06
    3:0.08
    4:0.04
    5:0.10
    6:0.09
    7:0.08
    8:0.08
    9:0.10
    10:0.10
    11:0.05
    Negative Logits
    College
    -1.50
     someday
    -1.40
     Hitch
    -1.40
     Babe
    -1.40
     brunch
    -1.33
     crappy
    -1.31
     Betty
    -1.27
     wellness
    -1.27
     Buddy
    -1.26
     Loving
    -1.25
    POSITIVE LOGITS
     Kazakh
    1.74
     ceasefire
    1.64
     Kremlin
    1.53
    kish
    1.52
    zbollah
    1.49
     mortar
    1.45
    anwhile
    1.43
    Syrian
    1.43
     Azerbai
    1.40
     Ankara
    1.39
    Activations Density 0.512%

    No Known Activations