© 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. 18043
    Prev
    Next
    INDEX
    Explanations

    phrases associated with major global events and power dynamics

    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
    0:0.10
    1:0.05
    2:0.15
    3:0.05
    4:0.04
    5:0.06
    6:0.09
    7:0.05
    8:0.18
    9:0.08
    10:0.04
    11:0.05
    Negative Logits
     Ballard
    -3.25
     Mahar
    -3.15
    ellar
    -3.12
    orney
    -3.00
    Shield
    -3.00
     Hag
    -2.98
     Tuls
    -2.95
     Shib
    -2.92
    District
    -2.91
     dispensaries
    -2.87
    POSITIVE LOGITS
     Nice
    6.13
    Nice
    5.17
    nice
    3.88
     Tunis
    3.67
     Euro
    3.60
     Portugal
    3.55
     Bast
    3.48
    �
    3.47
     Calais
    3.45
     Frenchman
    3.44
    Activations Density 0.001%

    No Known Activations