© 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. 13464
    Prev
    Next
    INDEX
    Explanations

    keywords related to the perception of social justice and elite influence

    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
    0:0.08
    1:0.22
    2:0.06
    3:0.04
    4:0.05
    5:0.03
    6:0.17
    7:0.09
    8:0.02
    9:0.05
    10:0.08
    11:0.06
    Negative Logits
    ayed
    -2.64
    drawn
    -2.62
     Lanka
    -2.42
     Animated
    -2.36
    actionDate
    -2.31
     dried
    -2.30
    theless
    -2.29
     Raymond
    -2.26
     mars
    -2.23
     [-
    -2.20
    POSITIVE LOGITS
     Elite
    6.78
     elite
    6.51
     elites
    4.94
    El
    3.51
    ilege
    3.42
     EL
    3.31
     el
    3.24
    Ultra
    3.18
     upper
    3.08
     Prest
    3.01
    Activations Density 0.007%

    No Known Activations