© 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. 10-ATT-KK
    11. 17447
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals and titles

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.14
    1:0.17
    2:0.08
    3:0.05
    4:0.06
    5:0.04
    6:0.06
    7:0.09
    8:0.04
    9:0.05
    10:0.11
    11:0.05
    Negative Logits
    Palest
    -3.39
    ffe
    -2.90
    CHA
    -2.82
     HAL
    -2.78
    rael
    -2.77
    Fal
    -2.76
     Fol
    -2.75
    phia
    -2.70
    Mont
    -2.66
     almond
    -2.65
    POSITIVE LOGITS
     Wick
    9.10
    ugal
    3.85
     Ack
    3.74
     Dill
    3.37
     Hung
    3.24
     Kamp
    3.24
     Eck
    3.19
     Budapest
    3.07
     Axel
    3.05
     Hungarian
    3.05
    Activations Density 0.000%

    No Known Activations