© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11659
    Prev
    Next
    INDEX
    Explanations

    references to religious leadership and doctrine

    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
    0:0.08
    1:0.01
    2:0.14
    3:0.07
    4:0.02
    5:0.08
    6:0.04
    7:0.05
    8:0.41
    9:0.02
    10:0.02
    11:0.01
    Negative Logits
     Ultron
    -3.60
     Kang
    -3.54
    Haw
    -3.40
    Tesla
    -3.33
    Pak
    -3.17
     Pak
    -3.12
     Hawth
    -3.06
    Atlanta
    -3.01
    ツ
    -3.00
     Asgard
    -2.98
    POSITIVE LOGITS
     Catholics
    7.75
    Catholic
    7.58
     Catholic
    7.54
     Vatican
    7.52
     pope
    7.46
     Catholicism
    7.39
     bishops
    7.19
    Pope
    6.85
     Sacrament
    6.78
     Pope
    6.73
    Activations Density 0.529%

    No Known Activations