© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 42920
    Prev
    Next
    INDEX
    Explanations

    references to exposure and its effects on health or the environment

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.05
    3:0.05
    4:0.06
    5:0.03
    6:0.04
    7:0.36
    8:0.03
    9:0.05
    10:0.13
    11:0.10
    Negative Logits
    ylum
    -1.55
     merging
    -1.45
    Delivery
    -1.43
    ivot
    -1.40
     reconc
    -1.38
     testament
    -1.38
    Rus
    -1.33
     simpl
    -1.33
    coord
    -1.31
     bride
    -1.29
    POSITIVE LOGITS
     ultraviolet
    1.54
     DOI
    1.48
     unfamiliar
    1.43
     exposure
    1.42
    quickShipAvailable
    1.40
     Manga
    1.39
    ForgeModLoader
    1.38
     Flavoring
    1.38
     allerg
    1.34
     radiation
    1.30
    Activations Density 0.008%

    No Known Activations