© 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. 10894
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical trends related to economics and demographics

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.02
    1:0.05
    2:0.05
    3:0.05
    4:0.10
    5:0.15
    6:0.05
    7:0.12
    8:0.03
    9:0.22
    10:0.06
    11:0.04
    Negative Logits
    Appearances
    -2.61
    tnc
    -2.56
    iris
    -2.45
    ulhu
    -2.45
    ワン
    -2.45
     violates
    -2.38
     fict
    -2.38
     wishes
    -2.37
    ossibility
    -2.34
    unity
    -2.29
    POSITIVE LOGITS
     averaging
    3.69
     topping
    3.42
     compared
    3.20
     Gallup
    3.15
     reflecting
    3.00
     boosting
    2.84
     versus
    2.83
     doubling
    2.80
     according
    2.79
     accounting
    2.72
    Activations Density 0.051%

    No Known Activations