© 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. 10-ATT-KK
    11. 6527
    Prev
    Next
    INDEX
    Explanations

    phrases related to uniqueness and customization in products

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.17
    1:0.08
    2:0.07
    3:0.05
    4:0.05
    5:0.03
    6:0.10
    7:0.13
    8:0.03
    9:0.04
    10:0.14
    11:0.05
    Negative Logits
     Missouri
    -3.14
     Aram
    -3.08
    Louis
    -2.81
     IPO
    -2.81
    log
    -2.70
     Petersen
    -2.56
    Reloaded
    -2.47
     Arkansas
    -2.46
     IPA
    -2.45
     Springfield
    -2.43
    POSITIVE LOGITS
     scarf
    6.00
     scar
    3.73
     Scar
    3.21
    scar
    3.15
     Garc
    3.08
    Scar
    3.07
     Cth
    3.05
     curls
    3.00
     Scarlet
    2.94
     Torch
    2.94
    Activations Density 0.002%

    No Known Activations