© 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. 9-ATT-KK
    11. 5594
    Prev
    Next
    INDEX
    Explanations

    political discussions and debates regarding governance and policy

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.18
    1:0.02
    2:0.15
    3:0.07
    4:0.02
    5:0.06
    6:0.03
    7:0.06
    8:0.27
    9:0.02
    10:0.02
    11:0.04
    Negative Logits
     Malays
    -3.51
    elaide
    -3.46
     Kuala
    -3.30
     Melbourne
    -3.29
    ibaba
    -3.25
     Gupta
    -3.23
    wana
    -3.13
    eva
    -3.06
     Johannes
    -3.04
     Indies
    -3.01
    POSITIVE LOGITS
     Boehner
    6.71
    hner
    4.47
     Speaker
    3.71
     Shutdown
    3.45
     caucus
    3.34
     Pelosi
    3.24
     Kasich
    3.19
    House
    3.17
     Caucus
    3.16
     Obamacare
    3.13
    Activations Density 0.013%

    No Known Activations