© 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. 10127
    Prev
    Next
    INDEX
    Explanations

    conjunctions and words indicating inclusivity or connection

    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
    0:0.12
    1:0.07
    2:0.09
    3:0.05
    4:0.16
    5:0.03
    6:0.07
    7:0.15
    8:0.02
    9:0.07
    10:0.06
    11:0.07
    Negative Logits
    Child
    -5.03
    Children
    -4.87
    child
    -4.76
     child
    -4.74
    children
    -4.45
     Child
    -4.38
     Children
    -4.23
     children
    -4.10
     pediatric
    -4.02
     toddler
    -3.93
    POSITIVE LOGITS
     Reeves
    4.11
     Reyes
    3.78
     Payne
    3.67
     Lowe
    3.48
     Tau
    3.45
     Fargo
    3.42
     Lange
    3.40
     Greene
    3.36
     Hayes
    3.31
     Hermes
    3.29
    Activations Density 0.002%

    No Known Activations