© 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. 9-ATT-KK
    11. 5708
    Prev
    Next
    INDEX
    Explanations

    topics related to aviation safety and incidents

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.39
    1:0.01
    2:0.13
    3:0.10
    4:0.02
    5:0.09
    6:0.02
    7:0.05
    8:0.09
    9:0.02
    10:0.02
    11:0.01
    Negative Logits
    Gamer
    -2.70
     Witcher
    -2.60
     crochet
    -2.50
     Wit
    -2.45
     Magicka
    -2.40
     Strawberry
    -2.36
     Publisher
    -2.35
     Mori
    -2.33
     Flesh
    -2.33
     stim
    -2.32
    POSITIVE LOGITS
     pilots
    5.12
     flight
    5.06
     aircraft
    5.05
     airliner
    4.98
    Flight
    4.92
     Airbus
    4.80
     takeoff
    4.80
     flying
    4.80
     flown
    4.77
     plane
    4.77
    Activations Density 0.860%

    No Known Activations