© 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. 3485
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and other function words in the text

    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
    0:0.06
    1:0.04
    2:0.07
    3:0.06
    4:0.05
    5:0.05
    6:0.26
    7:0.05
    8:0.08
    9:0.14
    10:0.04
    11:0.04
    Negative Logits
    BUS
    -3.95
    γ
    -3.54
    Crunch
    -3.45
     Portland
    -3.20
    �
    -3.18
    Portland
    -3.17
     defund
    -3.17
     [&
    -3.09
     Transit
    -3.06
     Blink
    -3.03
    POSITIVE LOGITS
     Manor
    7.94
     estates
    6.86
     Estate
    6.67
     estate
    6.25
     mansion
    5.87
     Mansion
    5.68
    estate
    4.78
     Norton
    4.55
     Loft
    4.53
     Monaco
    4.44
    Activations Density 0.001%

    No Known Activations