© 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. 47252
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and titles associated with people or organizations

    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
    0:0.02
    1:0.04
    2:0.02
    3:0.03
    4:0.02
    5:0.47
    6:0.01
    7:0.01
    8:0.04
    9:0.13
    10:0.11
    11:0.04
    Negative Logits
     Parenthood
    -1.73
    ||||
    -1.71
    birth
    -1.63
    イト
    -1.63
    incarn
    -1.62
    rican
    -1.61
     AAA
    -1.60
    foundland
    -1.58
    е
    -1.55
     piracy
    -1.54
    POSITIVE LOGITS
     concedes
    1.91
     admits
    1.89
     believes
    1.84
     concludes
    1.79
     concede
    1.75
     notes
    1.75
     stresses
    1.75
     recommends
    1.74
     says
    1.72
     conclud
    1.72
    Activations Density 0.746%

    No Known Activations