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. 20630
    Prev
    Next
    INDEX
    Explanations

    comparative and superlative forms related to beauty and appearance standards

    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
    0:0.06
    1:0.05
    2:0.10
    3:0.05
    4:0.04
    5:0.06
    6:0.25
    7:0.04
    8:0.04
    9:0.18
    10:0.03
    11:0.04
    Negative Logits
     Hanson
    -4.28
     truck
    -4.09
     Truck
    -4.01
     Freeman
    -3.88
     Trib
    -3.74
     Hels
    -3.74
    Rah
    -3.71
     Gand
    -3.54
     Dixon
    -3.53
     Atari
    -3.51
    POSITIVE LOGITS
    beaut
    7.62
     Beauty
    7.49
    Beaut
    7.44
     beauty
    6.70
     Beaut
    6.26
     beaut
    5.61
     Beautiful
    5.17
     beautiful
    4.92
    metics
    4.23
     cosmetic
    4.23
    Activations Density 0.003%

    No Known Activations