© 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. 10-ATT-KK
    11. 10859
    Prev
    Next
    INDEX
    Explanations

    terms related to social and economic issues, particularly those affecting marginalized communities

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.02
    3:0.03
    4:0.03
    5:0.15
    6:0.02
    7:0.02
    8:0.01
    9:0.56
    10:0.02
    11:0.04
    Negative Logits
    cing
    -2.11
    arling
    -2.04
    inating
    -2.03
    angu
    -2.00
    asuring
    -1.99
    ▬
    -1.91
    acing
    -1.86
    ising
    -1.85
    mos
    -1.85
     encrypt
    -1.84
    POSITIVE LOGITS
     she
    2.70
     he
    2.68
     they
    2.52
     saved
    2.48
     taken
    2.44
     we
    2.42
     shown
    2.40
     given
    2.33
     afforded
    2.33
     approved
    2.31
    Activations Density 0.911%

    No Known Activations