© 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. 17218
    Prev
    Next
    INDEX
    Explanations

    elements related to application structure and organization

    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
    0:0.04
    1:0.05
    2:0.05
    3:0.03
    4:0.03
    5:0.01
    6:0.04
    7:0.10
    8:0.04
    9:0.02
    10:0.47
    11:0.05
    Negative Logits
     Sho
    -3.06
    YC
    -2.77
     Shy
    -2.73
     C
    -2.71
    ���
    -2.66
    YR
    -2.65
     Esp
    -2.54
    lycer
    -2.53
     L
    -2.49
     ASP
    -2.48
    POSITIVE LOGITS
     d
    9.54
    d
    5.86
     ding
    4.68
     dd
    4.41
    ds
    4.24
    dt
    3.98
     t
    3.73
    dp
    3.64
     dun
    3.58
     dan
    3.57
    Activations Density 0.070%

    No Known Activations