© 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. 3-ATT-KK
    11. 5446
    Prev
    Next
    INDEX
    Explanations

    references to health-related risks and safety guidelines associated with infectious diseases and contaminants

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.04
    1:0.05
    2:0.07
    3:0.04
    4:0.08
    5:0.11
    6:0.09
    7:0.11
    8:0.11
    9:0.07
    10:0.09
    11:0.09
    Negative Logits
    ventures
    -1.20
    alogy
    -1.17
     Teach
    -1.13
     incorpor
    -1.13
     extraord
    -1.13
     mog
    -1.10
     Ninja
    -1.09
    Chair
    -1.08
    Nin
    -1.06
    aunt
    -1.05
    POSITIVE LOGITS
     unprotected
    1.41
     adversely
    1.32
     contaminated
    1.27
     alcohol
    1.25
     irreversible
    1.25
     pathogens
    1.24
     symptoms
    1.22
     expelled
    1.22
     evacuated
    1.22
     infected
    1.21
    Activations Density 0.181%

    No Known Activations