Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11427
    Prev
    Next
    INDEX
    Explanations

    country names and their associations, particularly in political contexts

    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
    1:0.03
    2:0.06
    3:0.07
    4:0.04
    5:0.07
    6:0.04
    7:0.05
    8:0.41
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
     NYPD
    -3.07
     Chinatown
    -2.77
     Liang
    -2.75
     Ahmad
    -2.71
     Shi
    -2.70
    asury
    -2.69
     MSG
    -2.66
     Nass
    -2.66
     Kahn
    -2.65
     Lau
    -2.61
    POSITIVE LOGITS
    Brazil
    3.94
     Peru
    3.71
     Paragu
    3.56
    Dutch
    3.16
     Brazil
    3.11
     Liberia
    3.06
     Lima
    3.03
     Colombia
    3.02
     Argentina
    3.01
     Congo
    2.92
    Activations Density 0.001%

    No Known Activations