© 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. 10854
    Prev
    Next
    INDEX
    Explanations

    quantifiable data or statistics

    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
    0:0.13
    1:0.16
    2:0.10
    3:0.05
    4:0.03
    5:0.02
    6:0.08
    7:0.15
    8:0.03
    9:0.03
    10:0.13
    11:0.03
    Negative Logits
     Cole
    -2.47
     Bis
    -2.42
    mare
    -2.40
     carb
    -2.21
     Lite
    -2.14
     Beat
    -2.11
    mares
    -2.10
    zy
    -2.08
     BAS
    -2.07
    actionDate
    -2.04
    POSITIVE LOGITS
     Reincarnated
    2.63
     Kerr
    2.29
     Elm
    2.21
    \/\/
    2.18
    Kenn
    2.12
     portraits
    2.02
    wcsstore
    2.00
    ansk
    1.96
    ctuary
    1.93
     Dialogue
    1.90
    Activations Density 0.002%

    No Known Activations