© 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. 6862
    Prev
    Next
    INDEX
    Explanations

    references to software updates and new applications for Windows operating systems

    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
    0:0.19
    1:0.06
    2:0.12
    3:0.10
    4:0.05
    5:0.02
    6:0.09
    7:0.08
    8:0.02
    9:0.04
    10:0.11
    11:0.08
    Negative Logits
     Barker
    -3.79
     Royals
    -3.50
     Yiannopoulos
    -3.36
     Koch
    -3.30
     Jagu
    -3.22
     Chavez
    -3.11
     Canter
    -3.09
     Tol
    -3.02
     Zar
    -2.90
     Pengu
    -2.87
    POSITIVE LOGITS
     Windows
    7.76
    Windows
    7.10
    windows
    6.40
     Microsoft
    5.77
     Lumia
    5.73
     Cortana
    5.60
    Microsoft
    5.56
    microsoft
    5.21
    WINDOWS
    5.14
     Redmond
    5.12
    Activations Density 0.124%

    No Known Activations