© 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. 38395
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.21
    1:0.07
    2:0.07
    3:0.08
    4:0.07
    5:0.08
    6:0.07
    7:0.03
    8:0.06
    9:0.07
    10:0.07
    11:0.06
    Negative Logits
    otin
    -2.16
    upload
    -2.02
    bold
    -2.01
    asta
    -1.96
    reve
    -1.76
    reply
    -1.74
    campaign
    -1.71
     piv
    -1.71
    responsive
    -1.70
    kat
    -1.70
    POSITIVE LOGITS
     Pt
    1.94
     Xue
    1.93
     Ley
    1.92
     Ezek
    1.88
     Roz
    1.87
    ーテ
    1.85
     Il
    1.84
     Mechdragon
    1.84
    Ire
    1.83
     Jade
    1.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.