© 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. 16989
    Prev
    Next
    INDEX
    Explanations

    references to the number of people on board various vehicles or vessels

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.04
    1:0.02
    2:0.09
    3:0.05
    4:0.06
    5:0.05
    6:0.08
    7:0.13
    8:0.04
    9:0.05
    10:0.07
    11:0.28
    Negative Logits
    IENCE
    -1.81
    aire
    -1.80
    pain
    -1.78
     assist
    -1.75
    assian
    -1.72
    hop
    -1.72
    leep
    -1.71
    ynchron
    -1.70
     lounge
    -1.67
     chores
    -1.66
    POSITIVE LOGITS
     MSM
    1.83
     Manafort
    1.83
     casing
    1.69
    arnaev
    1.61
    itbart
    1.59
    posing
    1.57
     Beir
    1.57
    powder
    1.55
    white
    1.54
     Baghd
    1.53
    Activations Density 0.001%

    No Known Activations