© 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. 9-ATT-KK
    11. 14834
    Prev
    Next
    INDEX
    Explanations

    references to governmental and judicial actions regarding dissent and political opposition

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

    No Comments

    Head Attr Weights
    0:0.10
    1:0.01
    2:0.19
    3:0.14
    4:0.04
    5:0.12
    6:0.02
    7:0.08
    8:0.15
    9:0.02
    10:0.04
    11:0.02
    Negative Logits
     Whitney
    -2.75
    Boston
    -2.71
    Ryan
    -2.56
     Lowell
    -2.52
     Tyler
    -2.46
    Tyler
    -2.45
     Spray
    -2.44
    maxwell
    -2.43
    Kelly
    -2.37
     Chevy
    -2.33
    POSITIVE LOGITS
     Mubarak
    4.66
     parliamentary
    4.37
     Morsi
    4.34
     democratically
    4.21
     parliament
    4.12
     dictatorship
    4.01
     elections
    3.79
     dictator
    3.59
    democracy
    3.58
     ANC
    3.55
    Activations Density 0.715%

    No Known Activations