© 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. 1029
    Prev
    Next
    INDEX
    Explanations

    specific dates and time-related phrases

    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
    0:0.03
    1:0.45
    2:0.02
    3:0.04
    4:0.03
    5:0.03
    6:0.08
    7:0.07
    8:0.03
    9:0.09
    10:0.03
    11:0.04
    Negative Logits
    maximum
    -3.17
    onga
    -2.99
    Already
    -2.80
    ctors
    -2.73
     Already
    -2.64
    minimum
    -2.60
    opal
    -2.56
     overdue
    -2.56
     Institution
    -2.54
    arers
    -2.52
    POSITIVE LOGITS
     1999
    5.23
     1998
    5.11
     1997
    5.10
     2001
    4.74
    1998
    4.70
     2000
    4.69
    1997
    4.49
    1999
    4.41
     97
    4.31
     2003
    4.23
    Activations Density 0.009%

    No Known Activations