© 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. 10-ATT-KK
    11. 19835
    Prev
    Next
    INDEX
    Explanations

    temporal references 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 @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.21
    1:0.03
    2:0.09
    3:0.10
    4:0.03
    5:0.02
    6:0.02
    7:0.29
    8:0.02
    9:0.04
    10:0.05
    11:0.04
    Negative Logits
     Columb
    -2.30
     gif
    -2.25
    yright
    -2.23
     þ
    -2.20
     Ragnar
    -2.18
    arnaev
    -2.17
    ð
    -2.14
    VK
    -2.12
     Balk
    -2.06
    Cy
    -2.06
    POSITIVE LOGITS
     Eisenhower
    2.72
     1954
    2.67
     Truman
    2.64
     1955
    2.54
     1956
    2.44
     1958
    2.40
     1953
    2.33
     1959
    2.30
     RF
    2.28
     1957
    2.24
    Activations Density 0.011%

    No Known Activations