© 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 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. 12836
    Prev
    Next
    INDEX
    Explanations

    references to acronyms and abbreviations, often related to organizations or entities

    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
    0:0.08
    1:0.02
    2:0.05
    3:0.12
    4:0.03
    5:0.06
    6:0.02
    7:0.05
    8:0.43
    9:0.02
    10:0.04
    11:0.04
    Negative Logits
     Suffolk
    -4.70
     Glou
    -4.14
     Berks
    -4.11
     Connecticut
    -4.04
    NJ
    -3.74
     Maryland
    -3.74
     NJ
    -3.69
     Delaware
    -3.67
     Worcester
    -3.65
     Rutgers
    -3.60
    POSITIVE LOGITS
     Yugoslav
    3.65
     Kremlin
    3.55
     Soy
    3.43
     Marxist
    3.39
     Lenin
    3.38
     Yugoslavia
    3.34
     Malays
    3.34
     Bolivia
    3.31
     Lavrov
    3.25
     Salvador
    3.23
    Activations Density 0.001%

    No Known Activations