© 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. 10-ATT-KK
    6. 15013
    Prev
    Next
    INDEX
    Explanations

    references to Turkey's energy policy and international relations

    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
    0:0.28
    1:0.03
    2:0.03
    3:0.10
    4:0.04
    5:0.02
    6:0.07
    7:0.12
    8:0.02
    9:0.04
    10:0.16
    11:0.03
    Negative Logits
     IBM
    -4.00
     Charleston
    -3.70
     Stard
    -3.59
     Holden
    -3.56
     Marty
    -3.49
     Vermont
    -3.40
     Lakers
    -3.39
     Payton
    -3.39
     Corvette
    -3.35
     LS
    -3.35
    POSITIVE LOGITS
     Ankara
    9.22
    Turkish
    8.93
     Turkish
    8.82
    Turkey
    8.82
     Erdogan
    8.78
     Turkey
    8.54
     Istanbul
    8.03
    stanbul
    7.46
    ğ
    7.42
     Turks
    7.35
    Activations Density 0.203%

    No Known Activations