© 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. 16457
    Prev
    Next
    INDEX
    Explanations

    instances of Islamic dress codes and regulations surrounding women's attire

    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
    1:0.01
    2:0.17
    3:0.08
    4:0.02
    5:0.10
    6:0.03
    7:0.05
    8:0.34
    9:0.03
    10:0.02
    11:0.02
    Negative Logits
     Hydro
    -3.36
     Bord
    -3.28
     Xperia
    -3.22
     CG
    -3.21
     Weaver
    -3.16
     Jagu
    -3.04
     Pike
    -3.00
     Cald
    -2.96
     Hank
    -2.94
     Tacoma
    -2.93
    POSITIVE LOGITS
     Quran
    8.32
    Muslims
    8.30
    Muslim
    8.27
     Muslim
    8.15
     Muslims
    8.12
     Islam
    8.12
    Islam
    7.99
     Koran
    7.58
     mosque
    7.57
    Islamic
    7.55
    Activations Density 0.477%

    No Known Activations