© 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. 10-ATT-KK
    11. 16158
    Prev
    Next
    INDEX
    Explanations

    references to religious texts or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.03
    2:0.07
    3:0.13
    4:0.13
    5:0.20
    6:0.04
    7:0.07
    8:0.03
    9:0.09
    10:0.04
    11:0.04
    Negative Logits
     downed
    -3.12
    ...]
    -3.04
     plummeted
    -3.03
    ]]
    -2.99
     froze
    -2.98
    !]
    -2.85
     toppled
    -2.76
     doomed
    -2.71
    kefeller
    -2.71
     soared
    -2.63
    POSITIVE LOGITS
     ¶
    2.83
     cf
    2.80
     Compare
    2.76
     );
    2.74
     ;
    2.68
    .).
    2.68
    .;
    2.67
     ).
    2.65
     Verse
    2.65
     §
    2.61
    Activations Density 0.011%

    No Known Activations