© 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. 18525
    Prev
    Next
    INDEX
    Explanations

    phrases related to official titles and roles within the White House and medical 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
    0:0.07
    1:0.03
    2:0.12
    3:0.06
    4:0.07
    5:0.04
    6:0.26
    7:0.05
    8:0.04
    9:0.17
    10:0.02
    11:0.02
    Negative Logits
     Antar
    -3.68
     Swan
    -3.44
     Falcon
    -3.41
     Sora
    -3.39
    wan
    -3.29
     Blair
    -3.29
     Dunn
    -3.27
     Angola
    -3.24
    Ru
    -3.17
     Scor
    -3.13
    POSITIVE LOGITS
     physicians
    7.91
     Doctors
    7.66
     doctors
    7.62
    Doctors
    7.39
     Physicians
    7.15
     physician
    7.06
    doctor
    6.80
     doctor
    6.70
     medicine
    6.65
     medical
    6.59
    Activations Density 0.042%

    No Known Activations