© 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. 30249
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal ownership and self-expression

    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
    0:0.02
    1:0.02
    2:0.11
    3:0.12
    4:0.25
    5:0.03
    6:0.12
    7:0.09
    8:0.04
    9:0.05
    10:0.06
    11:0.04
    Negative Logits
    anqu
    -1.90
    emort
    -1.70
    yip
    -1.65
    enance
    -1.61
    atibility
    -1.60
    eness
    -1.59
    ensitivity
    -1.57
    atism
    -1.56
    ariat
    -1.51
    ournal
    -1.50
    POSITIVE LOGITS
     euphem
    2.05
     shorthand
    1.73
     Vide
    1.70
     jargon
    1.64
     understatement
    1.62
    ��極
    1.58
     Logic
    1.57
     ital
    1.55
     analogy
    1.54
     Herz
    1.51
    Activations Density 0.000%

    No Known Activations