© 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. 9-ATT-KK
    11. 22618
    Prev
    Next
    INDEX
    Explanations

    topics related to historical tensions, conflicts, and significant events impacting nations

    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
    0:0.04
    1:0.01
    2:0.07
    3:0.45
    4:0.03
    5:0.11
    6:0.02
    7:0.05
    8:0.04
    9:0.02
    10:0.09
    11:0.01
    Negative Logits
     teammates
    -2.16
     onlook
    -2.09
    Interested
    -1.96
    relevant
    -1.87
     colleagues
    -1.81
     Ingredients
    -1.77
     deserving
    -1.77
     participating
    -1.76
    detail
    -1.76
     bystanders
    -1.75
    POSITIVE LOGITS
     riots
    3.00
     recession
    2.81
     wars
    2.76
     invasion
    2.73
    ixties
    2.71
     uprising
    2.66
     famine
    2.60
    ageddon
    2.56
     revolution
    2.51
     drought
    2.49
    Activations Density 1.457%

    No Known Activations