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. 9-ATT-KK
    6. 7629
    Prev
    Next
    INDEX
    Explanations

    references to bodily functions and physical sensations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.39
    1:0.02
    2:0.12
    3:0.12
    4:0.03
    5:0.05
    6:0.03
    7:0.04
    8:0.03
    9:0.02
    10:0.07
    11:0.01
    Negative Logits
     Skies
    -2.34
     Buildings
    -2.33
    Benz
    -2.31
     graphics
    -2.30
     Graphics
    -2.26
     screenshots
    -2.25
     HUD
    -2.24
     Vehicle
    -2.23
     pdf
    -2.22
     Residential
    -2.22
    POSITIVE LOGITS
     protr
    3.42
     swollen
    3.12
     braces
    3.02
     rupt
    2.98
     pierced
    2.91
     clenched
    2.90
     elastic
    2.86
    tight
    2.73
     lig
    2.72
    ache
    2.69
    Activations Density 0.122%

    No Known Activations