© 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. 12093
    Prev
    Next
    INDEX
    Explanations

    references to coding languages or specific coding standards

    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
    0:0.11
    1:0.19
    2:0.03
    3:0.03
    4:0.03
    5:0.02
    6:0.08
    7:0.10
    8:0.03
    9:0.02
    10:0.26
    11:0.05
    Negative Logits
     Ta
    -2.86
     Sterling
    -2.76
     Higgins
    -2.70
     lung
    -2.68
     Elk
    -2.68
     La
    -2.66
     Typ
    -2.60
     El
    -2.60
     Tah
    -2.50
     ath
    -2.47
    POSITIVE LOGITS
    pp
    5.14
    ppo
    4.03
    ppe
    3.59
    ppel
    3.29
    lp
    3.21
    PP
    3.16
    龍契士
    3.15
    upp
    3.07
     pp
    3.05
    ripp
    3.03
    Activations Density 0.001%

    No Known Activations