© 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. 6447
    Prev
    Next
    INDEX
    Explanations

    references to social justice and activism

    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
    0:0.12
    1:0.02
    2:0.11
    3:0.12
    4:0.05
    5:0.11
    6:0.03
    7:0.12
    8:0.11
    9:0.01
    10:0.11
    11:0.03
    Negative Logits
    iae
    -1.92
    inka
    -1.92
    otte
    -1.88
     contraceptive
    -1.79
     glim
    -1.78
     Vi
    -1.78
    NPR
    -1.76
     Copenhagen
    -1.71
    auna
    -1.68
    toggle
    -1.67
    POSITIVE LOGITS
     Jihad
    2.40
     Sorce
    2.21
     Baghd
    2.02
    Border
    1.94
    Islamic
    1.93
     Shinra
    1.93
     Pyramid
    1.82
     Sharia
    1.81
     Armageddon
    1.74
     Disciple
    1.74
    Activations Density 0.004%

    No Known Activations