© 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. 17336
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific breakthroughs and their implications

    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
    1:0.14
    2:0.05
    3:0.03
    4:0.02
    5:0.03
    6:0.12
    7:0.10
    8:0.02
    9:0.04
    10:0.18
    11:0.04
    Negative Logits
     tunnel
    -3.26
     tunnels
    -3.21
     NRS
    -3.14
     Lap
    -3.11
     Tunnel
    -2.87
     MT
    -2.84
     Warren
    -2.77
     TT
    -2.69
    aho
    -2.69
     Hath
    -2.67
    POSITIVE LOGITS
     Cris
    8.46
     Kris
    6.90
     cris
    4.38
    ris
    4.08
    Ir
    4.04
     Cros
    3.91
     Stras
    3.80
     Brus
    3.72
    icing
    3.57
     Cir
    3.49
    Activations Density 0.002%

    No Known Activations