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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15208
    Prev
    Next
    INDEX
    Explanations

    instances of page references and discussions on a variety of topics

    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
    0:0.06
    1:0.04
    2:0.12
    3:0.08
    4:0.04
    5:0.02
    6:0.11
    7:0.19
    8:0.02
    9:0.02
    10:0.04
    11:0.20
    Negative Logits
     Bell
    -1.99
     ����
    -1.90
    Bell
    -1.81
     Loch
    -1.80
    dayName
    -1.77
     Mae
    -1.77
     Costco
    -1.75
     Gould
    -1.75
     Bray
    -1.74
    estern
    -1.69
    POSITIVE LOGITS
     pages
    4.94
     Pages
    4.52
     page
    4.48
    pages
    4.31
    Pages
    4.09
     Page
    3.97
    page
    3.84
    Page
    3.69
     webpage
    3.25
     PAGE
    3.12
    Activations Density 0.043%

    No Known Activations