© 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. 2-ATT-KK
    11. 11473
    Prev
    Next
    INDEX
    Explanations

    mentions of generations in the context of workplace and societal trends, with a focus on Millennials and their relationship with automation and caregiving responsibilities

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.05
    1:0.11
    2:0.10
    3:0.07
    4:0.08
    5:0.09
    6:0.04
    7:0.05
    8:0.05
    9:0.20
    10:0.07
    11:0.03
    Negative Logits
     deposition
    -1.74
     Judicial
    -1.66
     cooperation
    -1.58
    RAW
    -1.54
     coordination
    -1.51
     suffice
    -1.51
     Torrent
    -1.49
     procedure
    -1.48
     interference
    -1.47
    UCT
    -1.46
    POSITIVE LOGITS
     Millennials
    2.05
     millennials
    1.87
     millennial
    1.75
    idges
    1.65
     EVs
    1.50
    kees
    1.48
    represented
    1.47
    obiles
    1.47
    pees
    1.45
     unaff
    1.44
    Activations Density 0.008%

    No Known Activations