© 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. 17172
    Prev
    Next
    INDEX
    Explanations

    sentences or clauses related to specific coding languages or technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.15
    2:0.03
    3:0.03
    4:0.03
    5:0.03
    6:0.05
    7:0.33
    8:0.02
    9:0.04
    10:0.10
    11:0.04
    Negative Logits
     Ley
    -2.39
     FI
    -2.38
     ly
    -2.29
     Pow
    -2.27
     Blanc
    -2.27
     pow
    -2.25
     Bundes
    -2.24
     Bog
    -2.20
    lit
    -2.16
     hig
    -2.16
    POSITIVE LOGITS
     Dhabi
    2.87
     Shotgun
    2.55
    assian
    2.46
    ija
    2.44
     DJs
    2.33
    Topics
    2.32
     newsletter
    2.30
     radar
    2.28
    azor
    2.27
    agle
    2.25
    Activations Density 0.003%

    No Known Activations