© 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. 10-ATT-KK
    11. 15587
    Prev
    Next
    INDEX
    Explanations

    references to NATO and its operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.21
    1:0.04
    2:0.06
    3:0.09
    4:0.04
    5:0.02
    6:0.19
    7:0.12
    8:0.01
    9:0.04
    10:0.06
    11:0.06
    Negative Logits
    HOU
    -3.24
     Alvin
    -3.11
    Houston
    -3.06
    ouston
    -3.02
    atown
    -2.88
     Negro
    -2.88
     Parish
    -2.79
    tx
    -2.78
     Pasadena
    -2.76
     dispensaries
    -2.69
    POSITIVE LOGITS
     NATO
    8.51
    NAT
    7.21
     Nato
    6.54
     Baltic
    5.82
     Monteneg
    5.09
     Lithuania
    4.91
     Estonia
    4.90
     Warsaw
    4.78
     Latvia
    4.76
     Allies
    4.64
    Activations Density 0.051%

    No Known Activations