© 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. 10919
    Prev
    Next
    INDEX
    Explanations

    references to streaming and access to multimedia content

    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
    0:0.08
    1:0.02
    2:0.09
    3:0.39
    4:0.03
    5:0.12
    6:0.02
    7:0.05
    8:0.04
    9:0.02
    10:0.07
    11:0.02
    Negative Logits
    ebin
    -2.38
    urden
    -2.17
    lihood
    -2.10
    gap
    -2.09
    iatus
    -2.09
    igslist
    -2.09
    govtrack
    -2.04
    cation
    -2.03
    chard
    -2.03
    epad
    -2.00
    POSITIVE LOGITS
     legends
    3.49
     personalities
    3.29
     classics
    3.28
     creations
    3.14
     inventions
    2.98
     innovations
    2.90
     iconic
    2.83
     characters
    2.83
     performers
    2.82
     icons
    2.79
    Activations Density 0.676%

    No Known Activations