© 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. 19849
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to voting rights and electoral processes

    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
    0:0.11
    1:0.12
    2:0.05
    3:0.06
    4:0.03
    5:0.02
    6:0.23
    7:0.08
    8:0.03
    9:0.04
    10:0.13
    11:0.05
    Negative Logits
    ayn
    -3.15
     Reds
    -3.13
     Schwar
    -3.09
     Flan
    -3.09
     Barbarian
    -2.92
    Brend
    -2.85
     Nou
    -2.85
     Fran
    -2.76
     Suarez
    -2.76
     Shanahan
    -2.74
    POSITIVE LOGITS
     Elect
    7.63
     elect
    7.35
    elect
    7.00
    Elect
    6.58
     ELECT
    5.91
     electing
    5.37
     Electro
    4.89
    lect
    4.75
     electors
    4.62
    LECT
    4.54
    Activations Density 0.003%

    No Known Activations