© 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. 7482
    Prev
    Next
    INDEX
    Explanations

    references to political unrest or governmental control in relation to specific incidents or actions

    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
    0:0.07
    1:0.01
    2:0.08
    3:0.09
    4:0.02
    5:0.06
    6:0.02
    7:0.05
    8:0.50
    9:0.02
    10:0.02
    11:0.01
    Negative Logits
    Irish
    -4.57
     Dublin
    -4.17
    Ireland
    -4.12
     Glasgow
    -4.00
     Irish
    -3.98
     Ireland
    -3.91
     Conor
    -3.89
     Columbus
    -3.88
     Cork
    -3.85
     Pike
    -3.71
    POSITIVE LOGITS
    Egypt
    8.24
     Mubarak
    8.04
     Egyptian
    7.90
     Morsi
    7.88
     Egyptians
    7.71
     Cairo
    7.57
     Egypt
    7.36
     Sinai
    6.86
     Nile
    6.67
     Pharaoh
    6.43
    Activations Density 0.200%

    No Known Activations