© 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. 10956
    Prev
    Next
    INDEX
    Explanations

    references to medical institutions or healthcare-related 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
    0:0.14
    1:0.01
    2:0.39
    3:0.08
    4:0.03
    5:0.11
    6:0.05
    7:0.05
    8:0.04
    9:0.03
    10:0.02
    11:0.01
    Negative Logits
     �
    -2.79
     Strongh
    -2.71
     rebell
    -2.41
     poaching
    -2.39
     secession
    -2.38
     Klux
    -2.37
     Theft
    -2.35
    ottenham
    -2.33
     Tradable
    -2.33
    Catalog
    -2.31
    POSITIVE LOGITS
    Doctors
    6.74
     patients
    6.72
     doctors
    6.66
     physicians
    6.45
     Patients
    6.41
     patient
    6.38
     Doctors
    6.31
     hospital
    6.22
     medical
    6.10
    patient
    6.04
    Activations Density 1.979%

    No Known Activations