© 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. 15126
    Prev
    Next
    INDEX
    Explanations

    references to original or inaugural events or entities

    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
    0:0.17
    1:0.11
    2:0.06
    3:0.18
    4:0.06
    5:0.02
    6:0.06
    7:0.06
    8:0.02
    9:0.04
    10:0.11
    11:0.05
    Negative Logits
    ovych
    -3.67
    "},"
    -3.22
     pol
    -3.22
     Baton
    -3.10
    POL
    -2.99
     Les
    -2.98
     lim
    -2.84
     bleach
    -2.83
     GOODMAN
    -2.83
     Pablo
    -2.82
    POSITIVE LOGITS
     Advent
    8.94
     Archangel
    3.93
     Seventh
    3.90
     evangel
    3.71
     Evangel
    3.58
     Celest
    3.35
     Cinnamon
    3.29
     Celestial
    3.26
     Apostles
    3.24
    Christmas
    3.16
    Activations Density 0.000%

    No Known Activations