© 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. 10-ATT-KK
    11. 20858
    Prev
    Next
    INDEX
    Explanations

    references to political candidates and electoral contexts

    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
    0:0.30
    1:0.03
    2:0.04
    3:0.08
    4:0.06
    5:0.02
    6:0.16
    7:0.07
    8:0.02
    9:0.05
    10:0.07
    11:0.05
    Negative Logits
     Sabres
    -4.09
    án
    -3.84
     Mei
    -3.65
     Czech
    -3.59
     Prague
    -3.55
     Slovakia
    -3.55
     contag
    -3.37
     Wings
    -3.33
    monary
    -3.28
     Krug
    -3.26
    POSITIVE LOGITS
     Moore
    8.34
    Moore
    8.29
     Alabama
    6.21
    Alabama
    5.88
     Ala
    5.26
    Roy
    5.04
     Roy
    4.72
     Bentley
    4.69
     Leigh
    4.50
     Montgomery
    4.46
    Activations Density 0.017%

    No Known Activations