© 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. 6503
    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
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.09
    3:0.09
    4:0.07
    5:0.09
    6:0.08
    7:0.08
    8:0.06
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
     sock
    -2.82
     Mog
    -2.73
     Somali
    -2.58
     colle
    -2.56
     Nguyen
    -2.49
    heter
    -2.47
    �
    -2.45
    �
    -2.44
    ipel
    -2.41
    doms
    -2.40
    POSITIVE LOGITS
    IPS
    2.61
     Letters
    2.57
     Freeze
    2.50
    rer
    2.46
     Correction
    2.44
     ATK
    2.43
    AE
    2.39
     forgiven
    2.37
    amus
    2.35
     restored
    2.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.