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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3054
    Prev
    Next
    INDEX
    Explanations

    details related to skin properties and their effects

    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
    0:0.26
    1:0.02
    2:0.19
    3:0.12
    4:0.03
    5:0.11
    6:0.03
    7:0.05
    8:0.04
    9:0.03
    10:0.03
    11:0.02
    Negative Logits
     Dispatch
    -2.46
    Narr
    -2.42
     Renault
    -2.41
     DeL
    -2.40
    Train
    -2.34
     Concord
    -2.34
     Economics
    -2.29
    pend
    -2.29
     Farming
    -2.21
     crates
    -2.20
    POSITIVE LOGITS
     acne
    4.48
     pores
    4.32
     wrinkles
    4.00
     skin
    3.94
     moistur
    3.87
     sunscreen
    3.80
     makeup
    3.78
     dermat
    3.61
     Skin
    3.52
     oily
    3.50
    Activations Density 0.066%

    No Known Activations