© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 13748
    Prev
    Next
    INDEX
    Explanations

    phrases related to the societal perception and treatment of fathers

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.20
    1:0.08
    2:0.05
    3:0.06
    4:0.05
    5:0.01
    6:0.10
    7:0.15
    8:0.02
    9:0.04
    10:0.12
    11:0.07
    Negative Logits
     Chandra
    -2.89
     dstg
    -2.86
     Amtrak
    -2.84
     traveler
    -2.80
    Burn
    -2.76
     Amon
    -2.75
     Burning
    -2.73
     Router
    -2.67
    trak
    -2.59
     Yun
    -2.58
    POSITIVE LOGITS
     dads
    6.08
     paternity
    5.41
     fathers
    4.58
     moms
    4.28
     parenting
    4.24
     paternal
    4.17
    aternal
    3.81
     Fathers
    3.77
     mothers
    3.73
     sperm
    3.68
    Activations Density 0.027%

    No Known Activations