© 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. 44056
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "world" or related concepts indicating a global perspective

    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
    0:0.02
    1:0.01
    2:0.18
    3:0.04
    4:0.05
    5:0.03
    6:0.05
    7:0.06
    8:0.10
    9:0.03
    10:0.19
    11:0.18
    Negative Logits
    ocious
    -1.76
     cure
    -1.60
    ixir
    -1.57
    ouf
    -1.54
     Cure
    -1.52
     Transformation
    -1.48
    ビ
    -1.46
     miracle
    -1.45
     resurrection
    -1.44
    olution
    -1.42
    POSITIVE LOGITS
    sites
    1.77
    Apps
    1.69
    abases
    1.68
     includ
    1.67
     folders
    1.58
    endars
    1.57
    apps
    1.57
    uthor
    1.57
    idates
    1.57
     favorites
    1.55
    Activations Density 0.013%

    No Known Activations