© 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. 9-ATT-KK
    11. 527
    Prev
    Next
    INDEX
    Explanations

    references to political and military tensions in international relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.07
    3:0.12
    4:0.07
    5:0.20
    6:0.05
    7:0.15
    8:0.06
    9:0.04
    10:0.04
    11:0.07
    Negative Logits
    soType
    -3.17
    Contract
    -3.13
    Consumer
    -2.81
    NYSE
    -2.77
    Employ
    -2.77
    ertation
    -2.75
    biz
    -2.74
    uner
    -2.73
    Market
    -2.68
    wcs
    -2.67
    POSITIVE LOGITS
     Syrian
    3.55
     Assad
    3.39
     Raqqa
    3.37
     YPG
    3.30
     Abbas
    3.19
     Kurdish
    3.02
     Kurds
    3.00
     Syria
    2.96
     Arab
    2.90
     Damascus
    2.88
    Activations Density 0.033%

    No Known Activations