© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 20710
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    0:0.17
    1:0.07
    2:0.07
    3:0.08
    4:0.07
    5:0.04
    6:0.11
    7:0.12
    8:0.03
    9:0.05
    10:0.10
    11:0.05
    Negative Logits
     Sheldon
    -3.80
     Jews
    -3.40
     Netanyahu
    -3.29
     Jewish
    -3.28
    jew
    -3.25
     Jew
    -3.23
     Goldstein
    -3.14
     synagogue
    -3.10
    Jews
    -3.08
     rabbi
    -3.08
    POSITIVE LOGITS
     Corpus
    3.08
     Mongo
    3.08
    Brazil
    3.06
     Brazilian
    2.94
    hyde
    2.88
     Dropbox
    2.87
     Fres
    2.80
    ão
    2.79
     Brazil
    2.75
     Silva
    2.72
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.