© 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. 554
    Prev
    Next
    INDEX
    Explanations

    articles and determiners in sentences referencing packages or items

    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
    0:0.12
    1:0.03
    2:0.05
    3:0.05
    4:0.03
    5:0.04
    6:0.24
    7:0.03
    8:0.04
    9:0.26
    10:0.03
    11:0.03
    Negative Logits
     Alec
    -4.12
     Kenobi
    -4.10
    Beck
    -4.08
     Lana
    -4.04
     Stro
    -3.96
     Derby
    -3.94
     Weed
    -3.93
     Reeves
    -3.76
     Twain
    -3.76
     Cena
    -3.75
    POSITIVE LOGITS
    packages
    8.41
     Package
    8.25
     packages
    7.92
    Package
    7.75
     package
    7.59
    package
    7.54
    Pack
    7.03
     PACK
    6.50
     Pack
    6.09
    pkg
    5.30
    Activations Density 0.002%

    No Known Activations