© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 8783
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their roles

    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
    0:0.24
    1:0.05
    2:0.04
    3:0.08
    4:0.05
    5:0.02
    6:0.07
    7:0.10
    8:0.01
    9:0.04
    10:0.23
    11:0.04
    Negative Logits
     Ballard
    -3.86
     Gree
    -3.78
     Bowman
    -3.65
    Seattle
    -3.61
     Murray
    -3.60
     Shanahan
    -3.60
     Sask
    -3.48
    okane
    -3.43
     Garry
    -3.41
     sled
    -3.38
    POSITIVE LOGITS
     Tunis
    10.42
     Tunisia
    9.46
     Tripoli
    5.32
     Alger
    4.86
     Algeria
    4.82
     Libyan
    4.74
     Libya
    4.72
     Tah
    4.71
     Tanz
    4.56
     Moroccan
    4.51
    Activations Density 0.003%

    No Known Activations