© 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. 10-ATT-KK
    11. 20809
    Prev
    Next
    INDEX
    Explanations

    references to religious beliefs and their impacts on social issues

    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
    0:0.41
    1:0.04
    2:0.03
    3:0.07
    4:0.09
    5:0.02
    6:0.09
    7:0.06
    8:0.01
    9:0.04
    10:0.04
    11:0.06
    Negative Logits
    assetsadobe
    -4.64
     Yards
    -3.45
     Sabres
    -3.27
     Gadget
    -3.27
     Cisco
    -3.27
    Diamond
    -3.21
     4096
    -3.21
     Morph
    -3.19
    netflix
    -3.16
     Missile
    -3.12
    POSITIVE LOGITS
     theological
    8.47
     church
    8.32
     Religious
    8.25
     Christians
    8.17
     Christianity
    8.15
     theology
    8.14
     bapt
    7.98
     churches
    7.95
     evangelical
    7.95
     religious
    7.91
    Activations Density 1.370%

    No Known Activations