© 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. 4510
    Prev
    Next
    INDEX
    Explanations

    names of places and organizations related to health and medicine

    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
    0:0.05
    1:0.02
    2:0.05
    3:0.23
    4:0.03
    5:0.05
    6:0.02
    7:0.08
    8:0.02
    9:0.02
    10:0.37
    11:0.01
    Negative Logits
    Years
    -2.58
     sooner
    -2.53
     afterward
    -2.42
    later
    -2.42
     Years
    -2.35
     someday
    -2.33
     later
    -2.31
     afterwards
    -2.20
     eventually
    -2.16
     occasion
    -2.12
    POSITIVE LOGITS
     lacks
    2.54
     consists
    2.40
     comprises
    2.27
    ibaba
    1.94
     lack
    1.92
     currently
    1.89
     excludes
    1.87
     inactive
    1.78
     exists
    1.78
     resides
    1.74
    Activations Density 0.156%

    No Known Activations