© 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. 11678
    Prev
    Next
    INDEX
    Explanations

    references to political leaders and their actions or positions

    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
    1:0.02
    2:0.10
    3:0.05
    4:0.03
    5:0.13
    6:0.05
    7:0.06
    8:0.32
    9:0.04
    10:0.04
    11:0.03
    Negative Logits
     Akron
    -2.85
     Cleveland
    -2.84
     Mayweather
    -2.81
    riz
    -2.77
     Mafia
    -2.76
    oman
    -2.75
     Toledo
    -2.72
    ć
    -2.72
    Newsletter
    -2.68
     Sly
    -2.67
    POSITIVE LOGITS
     Tasmania
    5.09
     Tasman
    4.71
     Greens
    4.62
     NZ
    4.39
     Kiw
    4.24
     Auckland
    4.00
     Canberra
    3.87
    uckland
    3.82
     Perth
    3.78
    Austral
    3.77
    Activations Density 0.010%

    No Known Activations