© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 16686
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations, events, or statistics related to governance and electoral outcomes

    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
    0:0.03
    1:0.02
    2:0.03
    3:0.04
    4:0.05
    5:0.27
    6:0.04
    7:0.04
    8:0.02
    9:0.33
    10:0.02
    11:0.06
    Negative Logits
    rather
    -2.39
    Otherwise
    -2.35
    Higher
    -2.24
     finer
    -2.20
     awa
    -2.08
    Leaks
    -2.08
    BACK
    -2.01
    beit
    -1.99
     nodd
    -1.97
    \/\/
    -1.95
    POSITIVE LOGITS
     due
    3.50
    due
    3.23
     because
    2.72
     bec
    2.42
    because
    2.42
     owing
    2.37
    thora
    2.31
     Due
    2.24
     amid
    2.16
    fell
    2.16
    Activations Density 0.099%

    No Known Activations