© 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. 14316
    Prev
    Next
    INDEX
    Explanations

    references to organizational names and significant numerical data related to activities

    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
    1:0.05
    2:0.04
    3:0.04
    4:0.04
    5:0.04
    6:0.16
    7:0.04
    8:0.05
    9:0.33
    10:0.03
    11:0.08
    Negative Logits
    di
    -3.98
    dar
    -3.93
    Di
    -3.70
    Pand
    -3.51
    Dar
    -3.38
    Cod
    -3.37
    ECD
    -3.36
    adan
    -3.32
     glim
    -3.32
     Eisen
    -3.22
    POSITIVE LOGITS
     USA
    7.70
    USA
    7.20
    usa
    5.18
    usat
    4.00
     UPS
    3.63
     PLUS
    3.54
     AMER
    3.51
     Amer
    3.47
     Powder
    3.39
     Simulator
    3.38
    Activations Density 0.003%

    No Known Activations