© 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. 22916
    Prev
    Next
    INDEX
    Explanations

    references to political and social issues, particularly those involving public sentiment and governance

    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
    0:0.01
    1:0.01
    2:0.02
    3:0.03
    4:0.04
    5:0.12
    6:0.01
    7:0.03
    8:0.01
    9:0.61
    10:0.01
    11:0.04
    Negative Logits
    axis
    -2.06
     Carbuncle
    -1.94
    agne
    -1.94
    stable
    -1.93
    avis
    -1.86
    atten
    -1.85
    trak
    -1.84
     Adinida
    -1.82
    JV
    -1.82
    anmar
    -1.81
    POSITIVE LOGITS
     about
    5.95
    about
    5.90
     ABOUT
    5.78
     About
    5.35
     regarding
    4.79
    About
    4.60
     concerning
    4.24
     Regarding
    3.65
     pertaining
    3.60
     relating
    3.42
    Activations Density 1.605%

    No Known Activations