© 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. 7639
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation and emotional expressions in dialogue

    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
    0:0.18
    1:0.04
    2:0.14
    3:0.04
    4:0.05
    5:0.03
    6:0.11
    7:0.11
    8:0.02
    9:0.07
    10:0.13
    11:0.03
    Negative Logits
     NAV
    -3.75
     Hispan
    -3.25
     Tact
    -3.16
     SAL
    -3.02
     monarch
    -2.97
     Baton
    -2.94
     Palm
    -2.94
     Windsor
    -2.93
     rotor
    -2.92
     ATF
    -2.87
    POSITIVE LOGITS
     Jenny
    8.35
     Penny
    3.63
     Cox
    3.61
     Jenna
    3.53
     Judd
    3.42
    ja
    3.37
     Jessica
    3.32
     Bj
    3.27
     Jensen
    3.24
     PB
    3.17
    Activations Density 0.001%

    No Known Activations