© 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. 38375
    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
    0:0.08
    1:0.07
    2:0.08
    3:0.06
    4:0.08
    5:0.09
    6:0.06
    7:0.08
    8:0.10
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
    actionDate
    -2.27
    soDeliveryDate
    -2.19
    catentry
    -2.13
    Next
    -2.12
    itect
    -2.10
    quickShipAvailable
    -1.97
    SPONSORED
    -1.89
    Offline
    -1.86
    voice
    -1.85
    next
    -1.83
    POSITIVE LOGITS
     ascert
    1.91
     abduction
    1.86
     eleph
    1.63
    iasis
    1.61
     Incident
    1.61
    duct
    1.57
     numbering
    1.57
    ibal
    1.57
     ferry
    1.57
     Adin
    1.56
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.