© 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. 6735
    Prev
    Next
    INDEX
    Explanations

    references to fantasy themes involving battles, survival, and adventure

    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
    0:0.04
    1:0.02
    2:0.06
    3:0.09
    4:0.18
    5:0.24
    6:0.02
    7:0.04
    8:0.03
    9:0.17
    10:0.02
    11:0.04
    Negative Logits
    upuncture
    -3.00
     Wem
    -2.93
    Newsletter
    -2.84
     Mostly
    -2.73
    ]);
    -2.73
    "))
    -2.71
    initely
    -2.69
    quickShipAvailable
    -2.66
    laughter
    -2.64
    ticket
    -2.62
    POSITIVE LOGITS
    !
    3.95
    venge
    3.74
    ─
    3.72
     foes
    3.64
     fearsome
    3.62
     awaits
    3.56
    !]
    3.36
    !:
    3.35
     yourselves
    3.31
     mutants
    3.29
    Activations Density 0.310%

    No Known Activations