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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 3196
    Prev
    Next
    INDEX
    Explanations

    references to significant locations or events, particularly those involving the Vatican

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.10
    1:0.25
    2:0.05
    3:0.04
    4:0.03
    5:0.16
    6:0.04
    7:0.03
    8:0.06
    9:0.08
    10:0.04
    11:0.06
    Negative Logits
    inav
    -2.42
    adan
    -1.97
    adas
    -1.89
    ochet
    -1.88
    itaire
    -1.87
     Canad
    -1.82
    ses
    -1.78
    hawks
    -1.75
    ras
    -1.72
    rers
    -1.69
    POSITIVE LOGITS
    Photo
    2.22
     referen
    2.08
    photo
    1.99
    actionDate
    1.97
     Photo
    1.95
     photo
    1.91
    ItemImage
    1.75
    Quote
    1.68
     PHOTO
    1.67
     photos
    1.64
    Activations Density 0.002%

    No Known Activations