© 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. 5-ATT-KK
    11. 41439
    Prev
    Next
    INDEX
    Explanations

    phrases indicating duration or continuity over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.06
    1:0.02
    2:0.11
    3:0.08
    4:0.14
    5:0.04
    6:0.23
    7:0.03
    8:0.07
    9:0.08
    10:0.04
    11:0.05
    Negative Logits
    umbn
    -1.37
    xit
    -1.34
    emort
    -1.19
    razen
    -1.16
    pez
    -1.09
    hesive
    -1.08
    ascript
    -1.07
    ゴン
    -1.07
    dfx
    -1.06
    clamation
    -1.04
    POSITIVE LOGITS
     accordingly
    1.27
     consequently
    1.18
     almost
    1.09
     quite
    1.08
     fewer
    1.08
     remarkably
    1.08
     understandably
    1.05
     Bowser
    1.03
    fortunately
    1.01
     strikingly
    1.00
    Activations Density 0.306%

    No Known Activations