© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11884
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to years in relation to events or statistics

    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
    0:0.12
    1:0.07
    2:0.10
    3:0.06
    4:0.02
    5:0.03
    6:0.17
    7:0.01
    8:0.02
    9:0.30
    10:0.03
    11:0.03
    Negative Logits
     Lieberman
    -3.68
     DVDs
    -3.46
     Fol
    -3.39
     vents
    -3.23
    884
    -3.17
     ATI
    -3.12
     Mosque
    -3.10
     Toledo
    -3.06
     Dome
    -3.06
     Armory
    -3.05
    POSITIVE LOGITS
    Pick
    7.44
     Pick
    7.07
     pick
    6.82
    pick
    6.54
    picking
    6.41
     picked
    6.05
     picking
    5.89
     Picks
    5.79
    picked
    5.78
     picks
    5.77
    Activations Density 0.011%

    No Known Activations