© 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. 21970
    Prev
    Next
    INDEX
    Explanations

    references to political regimes and their actions in a geopolitical context

    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
    0:0.07
    1:0.01
    2:0.10
    3:0.10
    4:0.03
    5:0.07
    6:0.04
    7:0.11
    8:0.32
    9:0.03
    10:0.04
    11:0.03
    Negative Logits
    aukee
    -3.39
     Omaha
    -3.18
    deck
    -2.99
     Quinn
    -2.94
     Anaheim
    -2.88
     Indiana
    -2.87
    Arizona
    -2.84
     Indianapolis
    -2.83
     Oregon
    -2.83
    Indiana
    -2.82
    POSITIVE LOGITS
     regime
    5.08
    Assad
    5.02
     Rouhani
    4.86
     Homs
    4.86
     Assad
    4.78
     Iranians
    4.75
     Hezbollah
    4.63
     Mubarak
    4.60
     Tehran
    4.60
     Venezuel
    4.43
    Activations Density 0.025%

    No Known Activations