© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 20942
    Prev
    Next
    INDEX
    Explanations

    geographical references and the count of nations mentioned

    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
    1:0.22
    2:0.02
    3:0.15
    4:0.03
    5:0.14
    6:0.02
    7:0.12
    8:0.12
    9:0.02
    10:0.03
    11:0.03
    Negative Logits
    iets
    -2.45
    ircraft
    -2.28
    armac
    -2.27
    idine
    -2.23
     locality
    -2.22
    endor
    -2.08
    repair
    -2.05
    patch
    -2.04
    oran
    -2.03
    ellar
    -2.02
    POSITIVE LOGITS
     Ecuador
    3.23
     Peru
    3.13
     Costa
    3.03
     Colombia
    3.01
     Paragu
    2.97
     Colombian
    2.82
     Uruguay
    2.77
     Argentine
    2.76
     Panama
    2.67
     Sierra
    2.63
    Activations Density 0.002%

    No Known Activations