© 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. 39758
    Prev
    Next
    INDEX
    Explanations

    terms related to delegates and voting processes in elections, particularly in the context of political primaries

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.02
    2:0.05
    3:0.05
    4:0.05
    5:0.05
    6:0.03
    7:0.05
    8:0.02
    9:0.08
    10:0.39
    11:0.11
    Negative Logits
     dystop
    -1.62
    ◼
    -1.49
     Orwell
    -1.48
     encount
    -1.48
    NK
    -1.47
     antidepressant
    -1.46
    plugins
    -1.45
     antiv
    -1.44
     apology
    -1.42
     tob
    -1.42
    POSITIVE LOGITS
    eligible
    2.12
    animous
    1.90
     votes
    1.82
     bloc
    1.81
     vote
    1.76
     voting
    1.73
     pledged
    1.69
     evenly
    1.61
     unanimous
    1.58
     holders
    1.58
    Activations Density 0.037%

    No Known Activations