© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5-ATT-KK
    11. 45167
    Prev
    Next
    INDEX
    Explanations

    mentions of countries, particularly references to China and Germany

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.02
    2:0.12
    3:0.17
    4:0.30
    5:0.02
    6:0.06
    7:0.03
    8:0.06
    9:0.04
    10:0.05
    11:0.05
    Negative Logits
     WATCHED
    -1.55
    urai
    -1.40
     sounded
    -1.39
     wont
    -1.37
    opa
    -1.35
     reminds
    -1.33
     reminded
    -1.32
     bye
    -1.31
    galitarian
    -1.30
     cannot
    -1.29
    POSITIVE LOGITS
    selves
    1.97
    angering
    1.51
    $.
    1.47
    etheless
    1.46
     detriment
    1.43
    due
    1.40
     ones
    1.36
    zie
    1.30
    anship
    1.30
    blown
    1.26
    Activations Density 0.036%

    No Known Activations