© 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. 3-ATT-KK
    11. 5292
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and the complexities surrounding them

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    references to familial relationships and maternal roles

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.08
    1:0.04
    2:0.04
    3:0.02
    4:0.08
    5:0.38
    6:0.09
    7:0.05
    8:0.04
    9:0.03
    10:0.09
    11:0.03
    Negative Logits
     Democr
    -2.00
    nce
    -1.82
    pmwiki
    -1.78
    merce
    -1.75
     suffice
    -1.73
    opus
    -1.72
     traged
    -1.70
    EStream
    -1.63
    yip
    -1.62
     piracy
    -1.57
    POSITIVE LOGITS
     her
    2.16
     herself
    2.03
     groom
    2.01
     his
    1.81
    his
    1.72
     himself
    1.69
     dreams
    1.68
     classmates
    1.67
    asso
    1.66
     His
    1.66
    Activations Density 0.263%

    No Known Activations