© 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. 23044
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of respect or disregard for norms, particularly in the context of politics or authority

    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
    0:0.05
    1:0.05
    2:0.07
    3:0.12
    4:0.08
    5:0.07
    6:0.04
    7:0.08
    8:0.03
    9:0.26
    10:0.07
    11:0.04
    Negative Logits
    �
    -3.43
     �
    -3.06
     ­
    -2.96
    ​
    -2.37
    Â
    -2.35
    ‎
    -2.30
     �
    -2.16
     ​
    -2.05
    Ã
    -2.04
    ­
    -2.00
    POSITIVE LOGITS
    ��
    2.85
     Leilan
    2.39
     Reloaded
    2.32
     nomine
    2.31
    Downloadha
    2.24
    luaj
    2.19
    ��
    2.13
    Its
    2.09
    kefeller
    2.07
     beware
    2.03
    Activations Density 2.608%

    No Known Activations