© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 38183
    Prev
    Next
    INDEX
    Explanations

    references to wasting time in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.05
    3:0.06
    4:0.14
    5:0.04
    6:0.06
    7:0.34
    8:0.04
    9:0.02
    10:0.07
    11:0.08
    Negative Logits
    eeper
    -1.49
    affiliated
    -1.43
    Si
    -1.37
    versions
    -1.36
    Son
    -1.36
     variant
    -1.35
    FINE
    -1.34
    ominated
    -1.32
    latable
    -1.30
     Variant
    -1.30
    POSITIVE LOGITS
     wasted
    1.97
     frivol
    1.78
     wast
    1.70
     precious
    1.67
     imagination
    1.65
    ngth
    1.61
     unnecessarily
    1.59
     Wast
    1.56
     judgment
    1.54
     misplaced
    1.49
    Activations Density 0.011%

    No Known Activations