© 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. 6419
    Prev
    Next
    INDEX
    Explanations

    references to family members, particularly grandparental figures

    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
    0:0.05
    1:0.09
    2:0.07
    3:0.06
    4:0.05
    5:0.04
    6:0.24
    7:0.02
    8:0.04
    9:0.25
    10:0.02
    11:0.02
    Negative Logits
     Cage
    -3.83
     Porn
    -3.78
     porn
    -3.66
     Sea
    -3.54
    Sexual
    -3.49
     Sexual
    -3.43
     Jones
    -3.36
    ara
    -3.34
     Scene
    -3.26
    CS
    -3.18
    POSITIVE LOGITS
     grandparents
    6.82
     grandmother
    6.77
     grandfather
    6.40
     grandson
    6.18
     grandma
    6.14
    grand
    5.66
     granddaughter
    5.63
     grandchildren
    5.44
    Grand
    4.87
     ancestor
    4.08
    Activations Density 0.002%

    No Known Activations