© 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. 39555
    Prev
    Next
    INDEX
    Explanations

    references to durations of time

    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
    0:0.14
    1:0.23
    2:0.05
    3:0.04
    4:0.03
    5:0.10
    6:0.06
    7:0.04
    8:0.04
    9:0.06
    10:0.08
    11:0.07
    Negative Logits
    thumbnails
    -2.17
    asso
    -1.86
    arrow
    -1.86
    IPS
    -1.84
    ivari
    -1.83
    Measure
    -1.82
    Quant
    -1.81
    Sche
    -1.81
    then
    -1.81
    Supplement
    -1.80
    POSITIVE LOGITS
     dead
    1.93
     inactive
    1.91
     usable
    1.87
     friendly
    1.86
     Rican
    1.82
     playable
    1.81
     elf
    1.79
     unstable
    1.79
     Dead
    1.78
     corp
    1.77
    Activations Density 0.000%

    No Known Activations