© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 13310
    Prev
    Next
    INDEX
    Explanations

    references to product features and specifications, particularly for technology products like Chromebooks

    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
    0:0.24
    1:0.06
    2:0.06
    3:0.05
    4:0.04
    5:0.04
    6:0.07
    7:0.11
    8:0.03
    9:0.05
    10:0.13
    11:0.06
    Negative Logits
     Rangers
    -3.71
     McMahon
    -3.46
     Feldman
    -3.39
     whiskey
    -3.34
     Daniels
    -3.31
     Bord
    -3.29
     Tyson
    -3.26
     Adin
    -3.25
     rye
    -3.14
     horses
    -3.09
    POSITIVE LOGITS
     Chromebook
    9.16
     Acer
    6.06
     Lenovo
    5.33
     Chrome
    5.31
     ASUS
    5.27
     Asus
    4.85
     MacBook
    4.79
     laptops
    4.77
     laptop
    4.73
    aptop
    4.21
    Activations Density 0.006%

    No Known Activations