© 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. 9-ATT-KK
    11. 5541
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals in a formal context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.07
    1:0.03
    2:0.05
    3:0.04
    4:0.05
    5:0.03
    6:0.24
    7:0.03
    8:0.08
    9:0.28
    10:0.01
    11:0.02
    Negative Logits
     Wells
    -4.11
     Erie
    -3.85
     Wiggins
    -3.84
    owicz
    -3.58
     Tent
    -3.56
     Ogre
    -3.55
     cyclist
    -3.54
     cyclists
    -3.54
     Schw
    -3.48
     Penn
    -3.43
    POSITIVE LOGITS
    Mal
    10.23
     Mal
    9.41
    MAL
    8.01
    mal
    7.74
     Malays
    7.28
     Malik
    6.52
     Malaysia
    6.34
     mal
    5.79
     Mali
    5.67
     Malaysian
    5.49
    Activations Density 0.017%

    No Known Activations