© 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. 17438
    Prev
    Next
    INDEX
    Explanations

    instances of strong and effective communication within various contexts

    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
    0:0.08
    1:0.24
    2:0.06
    3:0.08
    4:0.05
    5:0.03
    6:0.09
    7:0.07
    8:0.03
    9:0.03
    10:0.08
    11:0.11
    Negative Logits
    illegal
    -2.79
     unlawfully
    -2.75
     unofficial
    -2.69
     ante
    -2.69
    avin
    -2.65
    uckland
    -2.63
     illegal
    -2.60
    roxy
    -2.57
     illegally
    -2.54
     Illegal
    -2.54
    POSITIVE LOGITS
     Focus
    5.58
    Focus
    5.36
    focus
    5.15
     focused
    5.04
     focus
    4.89
    ocused
    4.59
     focusing
    4.34
    focused
    4.30
     concentrate
    3.98
     focuses
    3.90
    Activations Density 0.006%

    No Known Activations