© 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. 10-ATT-KK
    11. 23243
    Prev
    Next
    INDEX
    Explanations

    terms associated with mandatory evacuation protocols

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.19
    1:0.08
    2:0.04
    3:0.10
    4:0.05
    5:0.04
    6:0.09
    7:0.14
    8:0.02
    9:0.06
    10:0.07
    11:0.08
    Negative Logits
     dag
    -2.80
    angling
    -2.67
     Parallel
    -2.60
     infinity
    -2.58
     Patent
    -2.57
    organic
    -2.54
     assassin
    -2.50
    chery
    -2.42
     symmetry
    -2.38
     Phar
    -2.37
    POSITIVE LOGITS
     evac
    5.91
     evacuation
    5.29
     evacuated
    4.79
     evacuate
    4.46
     Edmonton
    4.11
     relocation
    3.63
    Ev
    3.52
     FEMA
    3.51
     Calgary
    3.44
     shelters
    3.41
    Activations Density 0.007%

    No Known Activations