© 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. 19084
    Prev
    Next
    INDEX
    Explanations

    references to emotional investment and personal connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.04
    1:0.01
    2:0.05
    3:0.06
    4:0.10
    5:0.03
    6:0.07
    7:0.37
    8:0.03
    9:0.03
    10:0.10
    11:0.06
    Negative Logits
     clock
    -1.54
     coding
    -1.54
     Clock
    -1.49
    species
    -1.48
    ItemThumbnailImage
    -1.38
     spelling
    -1.34
    _-
    -1.33
     navigating
    -1.33
     fingerprint
    -1.33
    CEPT
    -1.32
    POSITIVE LOGITS
    gall
    1.90
     unden
    1.87
     poured
    1.85
     encour
    1.82
    urized
    1.75
    wash
    1.73
     trough
    1.72
     buckets
    1.68
    ongyang
    1.61
     baths
    1.58
    Activations Density 0.006%

    No Known Activations