© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15721
    Prev
    Next
    INDEX
    Explanations

    statements related to public relations and promotional activities

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.30
    1:0.04
    2:0.06
    3:0.05
    4:0.05
    5:0.02
    6:0.06
    7:0.16
    8:0.04
    9:0.05
    10:0.09
    11:0.03
    Negative Logits
    Brew
    -3.27
     Kramer
    -3.27
     Muss
    -3.12
     Sagan
    -3.11
     Draco
    -3.04
     Buddhist
    -3.03
     lunar
    -3.01
     Hubbard
    -3.00
     Kush
    -2.99
     Carson
    -2.97
    POSITIVE LOGITS
     Ubisoft
    8.04
     Assassin
    5.95
    isoft
    5.52
    Ub
    5.10
     Assassins
    4.81
     Ou
    3.56
     Unity
    3.50
     Wii
    3.42
     Uncharted
    3.39
     Pascal
    3.38
    Activations Density 0.013%

    No Known Activations