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. 5-ATT-KK
    6. 35748
    Prev
    Next
    INDEX
    Explanations

    mentions of Scandinavian countries and their roles in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.04
    2:0.04
    3:0.06
    4:0.04
    5:0.11
    6:0.05
    7:0.03
    8:0.04
    9:0.06
    10:0.36
    11:0.10
    Negative Logits
    raq
    -1.82
    pite
    -1.68
    force
    -1.49
    stocks
    -1.49
     ISIL
    -1.47
    rogen
    -1.47
    iterator
    -1.47
    growth
    -1.44
     Qaeda
    -1.44
    idth
    -1.43
    POSITIVE LOGITS
     citizenship
    1.47
     peninsula
    1.45
     Doodle
    1.42
     hospitality
    1.39
     District
    1.38
     bilingual
    1.37
     decor
    1.36
     Judd
    1.35
     generosity
    1.35
     Dominican
    1.34
    Activations Density 0.022%

    No Known Activations