© 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. 10104
    Prev
    Next
    INDEX
    Explanations

    political dynamics and electoral strategies within party contests

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.01
    1:0.01
    2:0.11
    3:0.15
    4:0.11
    5:0.03
    6:0.02
    7:0.10
    8:0.04
    9:0.07
    10:0.18
    11:0.11
    Negative Logits
     slang
    -1.17
     deprecated
    -1.16
     exported
    -1.15
    BSD
    -1.10
     users
    -1.08
    sterdam
    -1.05
    Used
    -1.04
     usage
    -1.04
     crochet
    -1.03
    Produ
    -1.02
    POSITIVE LOGITS
     embattled
    1.49
     showdown
    1.36
    election
    1.31
     reelection
    1.29
     Priebus
    1.29
     looming
    1.29
     frontrunner
    1.28
     recess
    1.28
     someday
    1.25
     centrist
    1.23
    Activations Density 0.571%

    No Known Activations