© 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. 6677
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and structure, particularly related to class definitions and function constructs

    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
    0:0.21
    1:0.05
    2:0.10
    3:0.12
    4:0.08
    5:0.04
    6:0.06
    7:0.13
    8:0.06
    9:0.03
    10:0.04
    11:0.02
    Negative Logits
     cig
    -3.40
     Avenger
    -3.30
     Charleston
    -3.21
     Savior
    -3.21
     Guam
    -3.15
     DPR
    -3.14
     Blizz
    -3.08
     Firefly
    -3.04
     ****
    -3.04
     Mormons
    -3.01
    POSITIVE LOGITS
     =>
    5.10
    =>
    3.64
     Daesh
    3.39
    ql
    3.06
     mosa
    2.98
     Beirut
    2.95
     Sabha
    2.94
     GHC
    2.92
     ));
    2.91
    displayText
    2.87
    Activations Density 0.002%

    No Known Activations