© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 23865
    Prev
    Next
    INDEX
    Explanations

    names and titles of professionals and experts, particularly in medical and academic 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
    0:0.04
    1:0.01
    2:0.04
    3:0.54
    4:0.03
    5:0.07
    6:0.03
    7:0.04
    8:0.06
    9:0.02
    10:0.05
    11:0.02
    Negative Logits
     countries
    -2.63
     stadiums
    -2.50
     nations
    -2.44
     airplanes
    -2.34
     airports
    -2.33
     country
    -2.30
     railways
    -2.30
     republic
    -2.28
     cities
    -2.17
     leagues
    -2.15
    POSITIVE LOGITS
    HAEL
    3.12
    ��
    2.95
    ricia
    2.72
     Kathryn
    2.72
    田
    2.71
    aphael
    2.59
     Ernst
    2.58
    orio
    2.58
     Nguyen
    2.57
    yna
    2.55
    Activations Density 1.717%

    No Known Activations