© 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. 10-ATT-KK
    11. 12126
    Prev
    Next
    INDEX
    Explanations

    references to political discourse and election-related sentiments

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.04
    1:0.04
    2:0.06
    3:0.10
    4:0.22
    5:0.04
    6:0.12
    7:0.08
    8:0.03
    9:0.08
    10:0.02
    11:0.11
    Negative Logits
    sterdam
    -2.91
    apan
    -2.84
     Investigator
    -2.82
    ewitness
    -2.77
     Investigators
    -2.76
    uberty
    -2.69
    english
    -2.65
    Discover
    -2.65
    QL
    -2.64
    roximately
    -2.61
    POSITIVE LOGITS
     centrist
    5.46
     populist
    5.29
     populism
    5.06
     centr
    4.97
     electoral
    4.78
     Democrats
    4.72
     elector
    4.65
     voters
    4.51
     popul
    4.49
     Republicans
    4.47
    Activations Density 1.110%

    No Known Activations