© 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. 10-ATT-KK
    11. 23070
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sense of community and collective identity with emphasis on customization

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.15
    1:0.13
    2:0.09
    3:0.05
    4:0.05
    5:0.04
    6:0.07
    7:0.09
    8:0.04
    9:0.05
    10:0.13
    11:0.05
    Negative Logits
    ··
    -3.18
    ْ
    -3.11
    vernment
    -2.91
     Colbert
    -2.90
     Texans
    -2.86
    �
    -2.85
    incinn
    -2.77
     slur
    -2.76
    hyde
    -2.73
     filib
    -2.69
    POSITIVE LOGITS
     Myst
    7.91
     Mystic
    6.94
     mystic
    5.74
     myst
    4.48
     mystical
    4.36
     Monaco
    3.56
     Noct
    3.42
     Holo
    3.40
     Radiant
    3.36
     Quantum
    3.34
    Activations Density 0.001%

    No Known Activations