Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 20651
    Prev
    Next
    INDEX
    Explanations

    arguments related to the morality and impact of religion

    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
    0:0.05
    1:0.03
    2:0.12
    3:0.06
    4:0.07
    5:0.08
    6:0.23
    7:0.05
    8:0.08
    9:0.12
    10:0.02
    11:0.04
    Negative Logits
     Yards
    -5.18
     Nano
    -4.87
     Clay
    -4.40
    Yan
    -4.32
     Havana
    -3.72
    Snow
    -3.72
     Bronx
    -3.71
    Baltimore
    -3.70
     Decker
    -3.67
     nano
    -3.54
    POSITIVE LOGITS
     religion
    9.33
     religions
    9.14
     Religion
    8.94
     religious
    8.31
    religious
    8.24
     relig
    7.98
     Religious
    7.66
     faiths
    7.34
     atheism
    7.09
     atheists
    6.96
    Activations Density 0.092%

    No Known Activations