© 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. 16900
    Prev
    Next
    INDEX
    Explanations

    references to coups and political upheaval

    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
    0:0.15
    1:0.02
    2:0.27
    3:0.08
    4:0.02
    5:0.10
    6:0.03
    7:0.04
    8:0.11
    9:0.03
    10:0.07
    11:0.02
    Negative Logits
     Dairy
    -2.73
     Lowell
    -2.58
     shelters
    -2.57
     STD
    -2.56
     abstinence
    -2.51
    装
    -2.39
     Barrier
    -2.37
     breastfeeding
    -2.37
     finite
    -2.37
    STD
    -2.35
    POSITIVE LOGITS
     coup
    5.11
     overth
    4.43
     overthrow
    4.34
     democratically
    4.09
     topple
    3.91
     Coup
    3.74
     toppled
    3.69
     treason
    3.55
     topp
    3.54
     conspir
    3.41
    Activations Density 0.041%

    No Known Activations