© 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. 38244
    Prev
    Next
    INDEX
    Explanations

    mentions of alternate universes and expansive worlds in narrative 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
    0:0.02
    1:0.01
    2:0.06
    3:0.06
    4:0.05
    5:0.09
    6:0.03
    7:0.04
    8:0.06
    9:0.08
    10:0.29
    11:0.14
    Negative Logits
    autions
    -1.31
    asive
    -1.27
     Warrant
    -1.22
     Defensive
    -1.19
     ACL
    -1.19
     Hearing
    -1.18
     preventive
    -1.16
     rookie
    -1.16
     comeback
    -1.15
     Jury
    -1.14
    POSITIVE LOGITS
     inhabited
    1.80
     civilizations
    1.67
     populated
    1.66
     dwarves
    1.62
     grids
    1.60
     habitable
    1.54
    population
    1.53
     populate
    1.48
    dimension
    1.44
     NPCs
    1.40
    Activations Density 0.295%

    No Known Activations