© 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. 5-ATT-KK
    11. 27005
    Prev
    Next
    INDEX
    Explanations

    terms related to time and duration, particularly focusing on ongoing or repeated activities and the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.02
    2:0.08
    3:0.05
    4:0.17
    5:0.01
    6:0.11
    7:0.34
    8:0.05
    9:0.02
    10:0.04
    11:0.05
    Negative Logits
    ulo
    -1.55
    Moon
    -1.44
     behalf
    -1.39
     2030
    -1.39
    orney
    -1.34
    essen
    -1.31
    ku
    -1.28
    FIG
    -1.28
    ouse
    -1.27
    ften
    -1.26
    POSITIVE LOGITS
    cart
    1.59
     firsthand
    1.56
    ウス
    1.50
     derogatory
    1.46
     dating
    1.44
     Tend
    1.38
     awhile
    1.38
     stint
    1.38
     bruising
    1.35
     ticking
    1.34
    Activations Density 0.024%

    No Known Activations