© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 21458
    Prev
    Next
    INDEX
    Explanations

    words related to political statements and governmental changes

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

    No Comments

    Head Attr Weights
    0:0.09
    1:0.04
    2:0.05
    3:0.14
    4:0.11
    5:0.03
    6:0.16
    7:0.10
    8:0.03
    9:0.07
    10:0.04
    11:0.09
    Negative Logits
     Crew
    -3.18
    Crew
    -2.86
    Jamie
    -2.79
     Locations
    -2.77
     Columbus
    -2.71
    maxwell
    -2.70
     crochet
    -2.69
    Ohio
    -2.69
     Etsy
    -2.66
     Larson
    -2.66
    POSITIVE LOGITS
     Morsi
    5.22
     parliamentary
    5.00
     parliament
    4.88
     Mubarak
    4.78
     democratically
    4.54
     electoral
    4.45
     dictatorship
    4.41
     elections
    4.17
     democratic
    4.11
     ousted
    4.06
    Activations Density 0.448%

    No Known Activations