© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 30135
    Prev
    Next
    INDEX
    Explanations

    color descriptors related to people's appearances

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.22
    1:0.03
    2:0.08
    3:0.06
    4:0.07
    5:0.06
    6:0.05
    7:0.04
    8:0.14
    9:0.04
    10:0.07
    11:0.08
    Negative Logits
    soDeliveryDate
    -2.45
    Origin
    -2.10
    ファ
    -2.07
    arte
    -1.98
    Enh
    -1.86
    Shape
    -1.86
    lished
    -1.86
    Leaks
    -1.84
    uci
    -1.79
    DragonMagazine
    -1.78
    POSITIVE LOGITS
     sacks
    2.04
     helmet
    1.91
     boots
    1.91
     lectures
    1.77
     patches
    1.75
     mustache
    1.73
     goggles
    1.71
     abs
    1.70
     shoes
    1.69
     bumps
    1.66
    Activations Density 0.001%

    No Known Activations