© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 47254
    Prev
    Next
    INDEX
    Explanations

    phrases related to military units and their designations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.07
    3:0.04
    4:0.06
    5:0.03
    6:0.13
    7:0.34
    8:0.03
    9:0.03
    10:0.10
    11:0.07
    Negative Logits
     possibilities
    -1.73
     freezes
    -1.68
    soDeliveryDate
    -1.62
     deadlines
    -1.60
     vacancy
    -1.58
     gaps
    -1.57
     pauses
    -1.51
     jars
    -1.50
     fireplace
    -1.50
     options
    -1.48
    POSITIVE LOGITS
     Excellence
    1.79
    ��
    1.61
    Merit
    1.52
     Noise
    1.50
    �
    1.48
     Infantry
    1.46
     Regiment
    1.44
    XL
    1.44
    oyal
    1.43
    ACA
    1.42
    Activations Density 0.003%

    No Known Activations