© 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. 10813
    Prev
    Next
    INDEX
    Explanations

    direct references to political figures and their actions in the context of elections

    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
    0:0.22
    1:0.08
    2:0.04
    3:0.08
    4:0.05
    5:0.02
    6:0.12
    7:0.10
    8:0.02
    9:0.04
    10:0.13
    11:0.05
    Negative Logits
     ASD
    -3.79
     Brick
    -3.13
    �
    -3.07
     Tap
    -3.05
    �
    -2.94
    Shield
    -2.86
     tul
    -2.83
     Brach
    -2.78
     schizophren
    -2.75
    �
    -2.74
    POSITIVE LOGITS
     Gore
    9.49
    Bush
    4.18
     Kerry
    4.02
     Bush
    4.00
     Cheney
    3.78
     Rove
    3.65
     Gor
    3.36
     Rocky
    3.32
     Jeb
    3.28
     fossil
    3.13
    Activations Density 0.010%

    No Known Activations