© 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. 5-ATT-KK
    11. 39496
    Prev
    Next
    INDEX
    Explanations

    specific interrogative words or phrases

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.08
    1:0.06
    2:0.08
    3:0.08
    4:0.08
    5:0.07
    6:0.08
    7:0.08
    8:0.08
    9:0.09
    10:0.08
    11:0.09
    Negative Logits
    ���
    -2.09
    ��極
    -1.84
     inheritance
    -1.84
     Racial
    -1.71
     BALL
    -1.64
     Inher
    -1.64
     Dictionary
    -1.62
     Kurds
    -1.61
    Attribute
    -1.60
     Rabb
    -1.59
    POSITIVE LOGITS
    enegger
    1.95
    church
    1.93
    swick
    1.90
    worthy
    1.89
    ilion
    1.86
    jad
    1.83
    rist
    1.81
    tub
    1.79
    affiliated
    1.78
    ghan
    1.77
    Activations Density 0.000%

    No Known Activations