© 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. 19890
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical data related to voting and election statistics

    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
    0:0.16
    1:0.08
    2:0.07
    3:0.06
    4:0.04
    5:0.04
    6:0.12
    7:0.07
    8:0.02
    9:0.04
    10:0.17
    11:0.06
    Negative Logits
     Uzbek
    -3.66
     DPR
    -3.27
     Ul
    -3.00
     Nek
    -2.98
     Kyr
    -2.93
    oran
    -2.90
     SE
    -2.90
     Hed
    -2.77
     synd
    -2.73
     Rohingya
    -2.72
    POSITIVE LOGITS
    Champ
    9.34
     Champ
    9.20
     champagne
    5.01
    agne
    3.90
     Chic
    3.69
     champ
    3.64
     Cham
    3.63
    $$$$
    3.53
    wcs
    3.36
    wine
    3.35
    Activations Density 0.002%

    No Known Activations