© 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. 9-ATT-KK
    11. 17517
    Prev
    Next
    INDEX
    Explanations

    references to technology and application-related keywords

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

    No Comments

    Head Attr Weights
    0:0.11
    1:0.06
    2:0.07
    3:0.15
    4:0.05
    5:0.11
    6:0.06
    7:0.06
    8:0.09
    9:0.05
    10:0.04
    11:0.09
    Negative Logits
     dads
    -2.23
     deserts
    -2.22
     神
    -2.22
     lent
    -2.19
     acad
    -2.18
     Raf
    -2.12
     moms
    -2.12
     arsen
    -2.11
     daughters
    -2.03
     roy
    -2.02
    POSITIVE LOGITS
    Runtime
    2.87
     Console
    2.75
    Console
    2.73
    System
    2.71
     Runtime
    2.70
    ernel
    2.66
    Configuration
    2.59
     Package
    2.58
    Stack
    2.57
    Debug
    2.56
    Activations Density 0.003%

    No Known Activations