© 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. 4906
    Prev
    Next
    INDEX
    Explanations

    elements related to political events and controversies

    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
    0:0.06
    1:0.03
    2:0.06
    3:0.04
    4:0.04
    5:0.04
    6:0.27
    7:0.04
    8:0.08
    9:0.23
    10:0.02
    11:0.04
    Negative Logits
     sorce
    -4.50
     Poc
    -4.38
     Sorce
    -4.33
     Carth
    -4.02
     paras
    -3.92
     idol
    -3.78
     Christina
    -3.75
     Taj
    -3.71
     Jagu
    -3.63
    Saudi
    -3.58
    POSITIVE LOGITS
     Gray
    10.26
    Gray
    10.22
    gray
    7.62
     gray
    7.21
    Grey
    6.34
     Grey
    6.31
     grey
    5.98
    grey
    5.26
     Gordon
    4.46
    Brown
    4.37
    Activations Density 0.006%

    No Known Activations