© 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. 957
    Prev
    Next
    INDEX
    Explanations

    references to event structures and organization

    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
    1:0.05
    2:0.03
    3:0.25
    4:0.05
    5:0.08
    6:0.04
    7:0.04
    8:0.05
    9:0.03
    10:0.24
    11:0.03
    Negative Logits
     Converted
    -2.63
     Units
    -2.15
     Aging
    -2.13
     Survivors
    -2.11
     Struggle
    -1.92
    Eventually
    -1.91
     Months
    -1.90
     CONTIN
    -1.90
     Slowly
    -1.89
     Returning
    -1.83
    POSITIVE LOGITS
    best
    2.12
     widest
    2.12
    usual
    1.96
    most
    1.96
    imei
    1.96
     causation
    1.91
    eki
    1.83
    cellent
    1.81
     conject
    1.80
     advis
    1.80
    Activations Density 0.001%

    No Known Activations