Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14680
    Prev
    Next
    INDEX
    Explanations

    instances of greeting or welcoming expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.17
    1:0.08
    2:0.11
    3:0.05
    4:0.05
    5:0.04
    6:0.08
    7:0.08
    8:0.02
    9:0.06
    10:0.15
    11:0.05
    Negative Logits
    greSQL
    -3.21
    lance
    -2.89
    ikhail
    -2.81
     slic
    -2.81
     pg
    -2.78
    abases
    -2.74
    Marc
    -2.67
     Salmon
    -2.64
     calcium
    -2.63
     marines
    -2.62
    POSITIVE LOGITS
     Toby
    8.66
     Tob
    4.45
     Tot
    4.03
     Tick
    3.98
     Tinker
    3.92
     Tobias
    3.88
     Tara
    3.85
     Woody
    3.85
     Faw
    3.69
     Tou
    3.68
    Activations Density 0.001%

    No Known Activations