© 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. 9-ATT-KK
    11. 989
    Prev
    Next
    INDEX
    Explanations

    references to religious texts and doctrines

    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
    0:0.13
    1:0.02
    2:0.06
    3:0.28
    4:0.03
    5:0.07
    6:0.02
    7:0.05
    8:0.14
    9:0.02
    10:0.11
    11:0.03
    Negative Logits
     executives
    -2.54
     stoked
    -2.53
     affordable
    -2.50
     independents
    -2.39
     leverage
    -2.38
     businesses
    -2.33
     trucks
    -2.30
     staffing
    -2.30
     perks
    -2.30
     antennas
    -2.29
    POSITIVE LOGITS
     verse
    4.19
     Psal
    4.04
     Verse
    3.88
     inscription
    3.57
     verses
    3.50
     Testament
    3.41
     Scripture
    3.39
     poem
    3.35
     Commentary
    3.35
     Romans
    3.32
    Activations Density 0.118%

    No Known Activations