© 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. 251
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" in various contexts

    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
    0:0.15
    1:0.03
    2:0.04
    3:0.07
    4:0.07
    5:0.05
    6:0.23
    7:0.02
    8:0.05
    9:0.16
    10:0.02
    11:0.04
    Negative Logits
     Galile
    -2.82
     herds
    -2.79
     Pony
    -2.78
     iTunes
    -2.77
     Lip
    -2.75
     lip
    -2.61
    mys
    -2.56
     Guest
    -2.53
     pony
    -2.53
     arg
    -2.49
    POSITIVE LOGITS
     Herald
    4.66
     newspaper
    4.20
     Guardian
    3.45
     Nanto
    3.37
    erald
    3.28
     papers
    3.27
     paper
    3.16
     Telegraph
    3.15
     newspapers
    3.06
     Newspaper
    3.01
    Activations Density 0.013%

    No Known Activations