© 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. 15979
    Prev
    Next
    INDEX
    Explanations

    references to rallies and protests related to social justice issues

    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
    0:0.36
    1:0.02
    2:0.02
    3:0.08
    4:0.04
    5:0.04
    6:0.10
    7:0.12
    8:0.02
    9:0.05
    10:0.05
    11:0.03
    Negative Logits
     Zub
    -3.85
     Jinn
    -3.77
     Oman
    -3.69
     cellul
    -3.57
     Aqua
    -3.50
     MIDI
    -3.42
     Meteor
    -3.35
     Kubrick
    -3.26
     lakes
    -3.26
     quartz
    -3.24
    POSITIVE LOGITS
     Charlottesville
    8.20
    ottesville
    7.47
    Charl
    5.79
     KKK
    5.17
     Gillespie
    5.12
     Klan
    5.12
     Confederate
    5.00
    Virginia
    5.00
     McAuliffe
    4.95
     Virginia
    4.84
    Activations Density 0.012%

    No Known Activations