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

    Neuronpedia

    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. 14247
    Prev
    Next
    INDEX
    Explanations

    references to political candidates and their running mates

    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
    0:0.24
    1:0.03
    2:0.04
    3:0.04
    4:0.04
    5:0.03
    6:0.33
    7:0.06
    8:0.02
    9:0.04
    10:0.05
    11:0.04
    Negative Logits
    ukemia
    -3.40
     fundra
    -3.21
     LAW
    -3.08
    lisher
    -2.97
    Downloadha
    -2.84
     fundraising
    -2.82
     Karin
    -2.77
     Sweeney
    -2.75
     lenders
    -2.68
    ucha
    -2.67
    POSITIVE LOGITS
     Guards
    3.43
     UKIP
    3.33
     Powell
    3.26
     baggage
    3.25
     Ports
    3.21
     mate
    3.15
    Pack
    3.06
     Colossus
    2.91
     Wallace
    2.88
    det
    2.84
    Activations Density 0.001%

    No Known Activations