© 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. 10-ATT-KK
    11. 14147
    Prev
    Next
    INDEX
    Explanations

    mentions of Saudi Arabia and its geopolitical relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.02
    2:0.03
    3:0.10
    4:0.08
    5:0.02
    6:0.04
    7:0.37
    8:0.02
    9:0.03
    10:0.03
    11:0.12
    Negative Logits
     Supervisor
    -2.31
     Bulgar
    -2.31
     Ronnie
    -2.25
     mashed
    -2.20
    Nat
    -2.17
     Stef
    -2.10
     Franch
    -2.10
    arf
    -2.09
     Natasha
    -2.08
    anca
    -2.08
    POSITIVE LOGITS
    hemy
    2.77
     UAE
    2.76
    uds
    2.48
     Qatar
    2.47
     Kuwait
    2.46
     Nah
    2.42
     Oman
    2.38
     Bahrain
    2.34
     Boll
    2.31
    hare
    2.29
    Activations Density 0.036%

    No Known Activations