© 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. 12043
    Prev
    Next
    INDEX
    Explanations

    negative statements or implications

    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
    0:0.16
    1:0.05
    2:0.06
    3:0.11
    4:0.10
    5:0.03
    6:0.09
    7:0.12
    8:0.03
    9:0.05
    10:0.09
    11:0.07
    Negative Logits
     Mü
    -3.82
     Eur
    -3.29
     Syri
    -3.17
     Euro
    -3.11
     Gö
    -3.09
    Europe
    -2.98
     Ö
    -2.94
     �
    -2.92
     Merkel
    -2.91
     Euros
    -2.91
    POSITIVE LOGITS
    adelphia
    3.74
     Chinatown
    3.66
    Indiana
    3.50
     LAPD
    3.42
     Rhode
    3.35
     Cambod
    3.29
     Bangkok
    3.13
     Daniels
    3.09
     Indiana
    3.06
     Spokane
    3.03
    Activations Density 0.000%

    No Known Activations