© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 14464
    Prev
    Next
    INDEX
    Explanations

    topics related to meditation, mindfulness, awareness, and compassion in Buddhist and Hindu traditions

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    terms associated with meditation and spiritual practices

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.03
    1:0.04
    2:0.08
    3:0.09
    4:0.03
    5:0.06
    6:0.12
    7:0.24
    8:0.04
    9:0.04
    10:0.08
    11:0.07
    Negative Logits
    ttle
    -1.24
    �士
    -1.16
     skelet
    -1.12
     retali
    -1.09
    ��極
    -1.03
     Townsend
    -1.03
     Lauder
    -1.02
    sov
    -1.01
    etsk
    -1.01
     unmarked
    -1.01
    POSITIVE LOGITS
     Meditation
    1.65
     teaches
    1.51
     Teach
    1.50
     taught
    1.40
     mindfulness
    1.39
     meditation
    1.39
     Healing
    1.36
     abstinence
    1.35
     teaching
    1.34
     mantra
    1.33
    Activations Density 0.034%

    No Known Activations