© 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. 10-ATT-KK
    11. 15188
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.03
    2:0.03
    3:0.10
    4:0.20
    5:0.07
    6:0.04
    7:0.08
    8:0.02
    9:0.10
    10:0.04
    11:0.08
    Negative Logits
     Strongh
    -3.05
    ahime
    -3.05
    ramid
    -2.99
     Diversity
    -2.73
    flags
    -2.56
    skirts
    -2.50
    hon
    -2.47
    itage
    -2.46
    atana
    -2.42
     spoof
    -2.40
    POSITIVE LOGITS
    Doctors
    5.41
     pneumonia
    5.02
     doctors
    5.00
     chemotherapy
    4.90
     neurolog
    4.81
     medication
    4.71
     hospital
    4.63
     symptoms
    4.60
     vomiting
    4.51
     ana
    4.47
    Activations Density 0.399%

    No Known Activations