© 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. 23187
    Prev
    Next
    INDEX
    Explanations

    connectors and transitional phrases within sentences

    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
    0:0.17
    1:0.06
    2:0.11
    3:0.04
    4:0.04
    5:0.03
    6:0.09
    7:0.11
    8:0.02
    9:0.04
    10:0.18
    11:0.07
    Negative Logits
     Asheville
    -3.05
    Roberts
    -2.72
     UNC
    -2.72
    hower
    -2.71
     Robertson
    -2.61
    Thom
    -2.59
     evangel
    -2.57
    olicy
    -2.53
     saturation
    -2.51
     primates
    -2.47
    POSITIVE LOGITS
     Maz
    9.53
     Haz
    6.20
     Raz
    6.00
     Laz
    4.64
     Uz
    4.59
     Miz
    4.43
     Mazda
    4.22
     Koz
    4.14
     Maul
    4.11
     Iz
    4.04
    Activations Density 0.002%

    No Known Activations