© 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. 5-ATT-KK
    11. 10099
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "be" and phrases involving existence or state of being

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.15
    1:0.12
    2:0.03
    3:0.03
    4:0.03
    5:0.17
    6:0.06
    7:0.04
    8:0.11
    9:0.06
    10:0.08
    11:0.06
    Negative Logits
     echoed
    -1.61
    76561
    -1.60
    883
    -1.56
     echoes
    -1.53
    >:
    -1.53
    PI
    -1.52
    Enlarge
    -1.51
     Lambert
    -1.49
     incre
    -1.49
    544
    -1.49
    POSITIVE LOGITS
     healthier
    1.91
    iosity
    1.90
    ocial
    1.86
    ohydrate
    1.79
    hip
    1.77
    thood
    1.75
     healthy
    1.74
     befriend
    1.72
     excel
    1.71
    cientious
    1.62
    Activations Density 0.013%

    No Known Activations