© 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. 9-ATT-KK
    11. 5773
    Prev
    Next
    INDEX
    Explanations

    phrases related to the severity and impact of storms and hurricanes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.07
    1:0.01
    2:0.45
    3:0.08
    4:0.03
    5:0.08
    6:0.04
    7:0.05
    8:0.09
    9:0.02
    10:0.03
    11:0.01
    Negative Logits
     transsexual
    -3.54
    emale
    -3.53
     Acquisition
    -3.13
     Chess
    -3.10
    Sex
    -2.94
    ethical
    -2.93
    ovo
    -2.86
     Philosophy
    -2.83
    xual
    -2.79
     prostate
    -2.78
    POSITIVE LOGITS
     hurricane
    5.74
     tornado
    5.44
     storms
    5.43
     hurricanes
    5.28
     floods
    5.03
     evacuation
    4.89
     evac
    4.88
     meteor
    4.83
     storm
    4.82
     Hurricane
    4.79
    Activations Density 0.826%

    No Known Activations