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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 44158
    Prev
    Next
    INDEX
    Explanations

    topics related to romantic relationships and their complexities

    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
    2:0.03
    3:0.04
    4:0.04
    5:0.07
    6:0.02
    7:0.04
    8:0.03
    9:0.09
    10:0.40
    11:0.15
    Negative Logits
     Archae
    -1.41
    oggles
    -1.32
    modules
    -1.27
     stadiums
    -1.27
    effects
    -1.25
    asive
    -1.25
    icons
    -1.24
     archaeologists
    -1.23
     pollutants
    -1.21
    RGB
    -1.21
    POSITIVE LOGITS
     roommate
    1.61
     boyfriend
    1.61
     lover
    1.60
     spouse
    1.55
     fiance
    1.47
     husband
    1.45
     Loving
    1.36
     reunion
    1.35
     friendship
    1.35
     bedroom
    1.34
    Activations Density 0.451%

    No Known Activations