© 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 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. 27886
    Prev
    Next
    INDEX
    Explanations

    references to demilitarized zones

    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
    0:0.01
    1:0.01
    2:0.05
    3:0.03
    4:0.04
    5:0.02
    6:0.17
    7:0.26
    8:0.03
    9:0.03
    10:0.25
    11:0.04
    Negative Logits
    ruby
    -1.99
    ONY
    -1.87
    tis
    -1.83
    rences
    -1.78
    ��
    -1.70
    Legendary
    -1.68
    ��
    -1.67
    opal
    -1.62
     Curious
    -1.62
    Magikarp
    -1.62
    POSITIVE LOGITS
     militar
    2.27
     Borders
    2.18
    ilitary
    2.16
     borders
    2.08
     paramilitary
    2.08
     arming
    2.01
     NATO
    1.91
     PLA
    1.89
     separating
    1.89
     airspace
    1.88
    Activations Density 0.001%

    No Known Activations