© 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. 15294
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their contributions, particularly in a professional or artistic context

    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
    0:0.02
    1:0.02
    2:0.06
    3:0.05
    4:0.26
    5:0.15
    6:0.06
    7:0.03
    8:0.13
    9:0.10
    10:0.02
    11:0.02
    Negative Logits
    ').
    -2.56
     '.
    -2.42
     cosmetic
    -2.38
    '-
    -2.36
    .'
    -2.30
     whereabouts
    -2.30
     omission
    -2.27
    PLE
    -2.21
     clutter
    -2.17
     immedi
    -2.14
    POSITIVE LOGITS
    auld
    2.79
     via
    2.55
    MQ
    2.42
    Posted
    2.32
     Average
    2.31
     skept
    2.25
     blogger
    2.24
    blog
    2.21
    Average
    2.17
    schild
    2.14
    Activations Density 0.001%

    No Known Activations