© 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. 9-ATT-KK
    11. 18138
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.09
    2:0.05
    3:0.05
    4:0.04
    5:0.04
    6:0.26
    7:0.03
    8:0.03
    9:0.26
    10:0.02
    11:0.03
    Negative Logits
     Phillips
    -3.92
     Hayes
    -3.58
     Laurel
    -3.57
     Berk
    -3.53
     recharge
    -3.35
    Phill
    -3.34
     Amir
    -3.25
     Ezra
    -3.24
     Cassidy
    -3.21
     Carroll
    -3.19
    POSITIVE LOGITS
    World
    5.45
     World
    5.38
     WORLD
    5.23
     Worlds
    4.96
    world
    4.87
     WTO
    4.32
    orld
    4.25
     WWF
    3.97
    WOR
    3.90
     worlds
    3.88
    Activations Density 0.013%

    No Known Activations