© 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. 9-ATT-KK
    11. 3863
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical tensions and threats related to Moldova's security and sovereignty

    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
    1:0.03
    2:0.10
    3:0.05
    4:0.06
    5:0.04
    6:0.14
    7:0.08
    8:0.15
    9:0.13
    10:0.04
    11:0.05
    Negative Logits
     Angels
    -3.73
    APD
    -3.67
    ゴン
    -3.40
    phrine
    -3.34
    Su
    -3.25
    su
    -3.23
     Scully
    -3.19
     shark
    -3.17
     sharks
    -3.16
    ��
    -3.10
    POSITIVE LOGITS
     Mold
    9.88
     Belarus
    5.55
     Latvia
    5.07
     Romania
    4.92
     Malk
    4.78
     mold
    4.78
     Buch
    4.61
     Lithuan
    4.59
     Monteneg
    4.53
     Lithuania
    4.50
    Activations Density 0.003%

    No Known Activations