© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 39489
    Prev
    Next
    INDEX
    Explanations

    mentions of political candidates and their associated actions or statements

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.02
    3:0.05
    4:0.02
    5:0.06
    6:0.01
    7:0.02
    8:0.02
    9:0.11
    10:0.44
    11:0.15
    Negative Logits
    pload
    -1.39
     Tok
    -1.29
     Anime
    -1.27
     Yam
    -1.27
     tenancy
    -1.26
    Cra
    -1.25
     Corsair
    -1.24
     Scrolls
    -1.22
    athi
    -1.22
    raq
    -1.21
    POSITIVE LOGITS
     frontrunner
    1.81
     challenger
    1.73
     candidacy
    1.72
     Candidate
    1.71
     campaign
    1.70
     candidate
    1.64
     presidency
    1.63
     voters
    1.63
     campaigned
    1.61
     presidential
    1.60
    Activations Density 1.645%

    No Known Activations