© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 42151
    Prev
    Next
    INDEX
    Explanations

    references to Islam and its interpretations, particularly focusing on its teachings and the beliefs of practicing Muslims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.01
    2:0.04
    3:0.05
    4:0.05
    5:0.05
    6:0.04
    7:0.05
    8:0.03
    9:0.07
    10:0.34
    11:0.18
    Negative Logits
     Seah
    -1.42
    ammy
    -1.23
    iband
    -1.21
    EEK
    -1.21
    iker
    -1.19
    inelli
    -1.18
    ORK
    -1.17
     YORK
    -1.16
    went
    -1.16
    Crew
    -1.13
    POSITIVE LOGITS
     polygamy
    1.52
     Sharia
    1.48
     civilized
    1.47
     barbaric
    1.39
     teachings
    1.38
     relig
    1.35
     patriarchal
    1.33
     ensl
    1.31
     millennia
    1.30
     bless
    1.30
    Activations Density 0.068%

    No Known Activations