© 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. 5-ATT-KK
    11. 40995
    Prev
    Next
    INDEX
    Explanations

    references to holes and their characteristics or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.01
    2:0.08
    3:0.06
    4:0.07
    5:0.04
    6:0.07
    7:0.07
    8:0.06
    9:0.05
    10:0.32
    11:0.07
    Negative Logits
     vitamins
    -2.07
    metics
    -2.00
     ambassadors
    -1.93
     export
    -1.86
     brands
    -1.84
     adject
    -1.81
     virtues
    -1.79
     commercials
    -1.69
     magazines
    -1.66
     acron
    -1.65
    POSITIVE LOGITS
    closure
    1.96
     uncovered
    1.66
    duction
    1.65
     shaft
    1.64
     excavation
    1.61
    ensional
    1.60
    iframe
    1.59
     ooz
    1.55
     reopened
    1.54
     disappears
    1.54
    Activations Density 0.006%

    No Known Activations