© 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. 8191
    Prev
    Next
    INDEX
    Explanations

    punctuation and quoted speech in dialogue or statements

    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
    0:0.16
    1:0.10
    2:0.05
    3:0.04
    4:0.04
    5:0.03
    6:0.06
    7:0.05
    8:0.03
    9:0.04
    10:0.29
    11:0.05
    Negative Logits
     Kingston
    -3.90
     Jinn
    -3.37
     Arist
    -3.20
     Hatt
    -3.02
     Jelly
    -2.97
     Kik
    -2.92
     Shan
    -2.89
     Jam
    -2.87
     Phil
    -2.83
    rican
    -2.82
    POSITIVE LOGITS
     Ve
    7.99
     ve
    7.66
    Ve
    7.29
    ve
    6.69
    VE
    5.50
     VG
    5.10
     Veg
    4.82
     Veget
    4.54
     Veil
    4.53
     veget
    4.41
    Activations Density 0.032%

    No Known Activations