© 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. 8575
    Prev
    Next
    INDEX
    Explanations

    questions and critical statements regarding political dynamics and electoral processes

    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
    0:0.17
    1:0.09
    2:0.11
    3:0.04
    4:0.03
    5:0.03
    6:0.15
    7:0.07
    8:0.03
    9:0.04
    10:0.17
    11:0.03
    Negative Logits
     Spartans
    -3.19
     Spartan
    -3.19
    agin
    -3.16
    ennes
    -3.00
    Sch
    -2.94
    earchers
    -2.93
    �
    -2.87
     Marketable
    -2.85
    BY
    -2.81
     Lansing
    -2.79
    POSITIVE LOGITS
     Rafael
    9.74
     Raf
    6.93
     Ricardo
    4.74
     Raz
    4.30
     Roland
    4.22
     Raphael
    4.08
     Rodrigo
    4.07
     Salvador
    4.06
     Fidel
    4.04
     Maur
    3.93
    Activations Density 0.005%

    No Known Activations