© 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. 39716
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing principles, particularly those related to governance and rights

    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
    0:0.01
    1:0.01
    2:0.06
    3:0.04
    4:0.06
    5:0.01
    6:0.10
    7:0.39
    8:0.02
    9:0.02
    10:0.11
    11:0.09
    Negative Logits
    bucks
    -1.86
    inventoryQuantity
    -1.69
     flashbacks
    -1.48
    abouts
    -1.47
     hordes
    -1.47
    ebin
    -1.46
     pulses
    -1.40
    anke
    -1.37
    ebook
    -1.36
    endars
    -1.34
    POSITIVE LOGITS
     Principles
    1.79
     principles
    1.56
     decency
    1.55
     Harmon
    1.53
    determination
    1.51
     neutrality
    1.50
    clus
    1.49
     Electrical
    1.48
    cellence
    1.47
    ���
    1.47
    Activations Density 0.012%

    No Known Activations