© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 8571
    Prev
    Next
    INDEX
    Explanations

    references to clothing and its cultural implications

    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
    0:0.21
    1:0.05
    2:0.08
    3:0.06
    4:0.04
    5:0.02
    6:0.12
    7:0.12
    8:0.03
    9:0.04
    10:0.08
    11:0.09
    Negative Logits
     glim
    -3.14
     │
    -2.98
     appar
    -2.93
     aval
    -2.89
     arom
    -2.87
     Morrow
    -2.78
     fortun
    -2.76
     CPC
    -2.75
     Lum
    -2.63
     Lama
    -2.61
    POSITIVE LOGITS
     shirts
    6.54
     shirt
    6.44
     Shirt
    6.04
    shirt
    5.50
    shirts
    4.90
    hirt
    4.42
     Adidas
    4.30
     Tee
    4.15
     jersey
    4.05
     tee
    4.01
    Activations Density 0.008%

    No Known Activations