© 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. 9-ATT-KK
    11. 5620
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to controversy and division

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.02
    3:0.13
    4:0.02
    5:0.04
    6:0.02
    7:0.05
    8:0.02
    9:0.01
    10:0.58
    11:0.01
    Negative Logits
    irtual
    -1.83
     to
    -1.72
    ordering
    -1.71
     urge
    -1.71
    reviewed
    -1.67
    accessible
    -1.66
    to
    -1.66
     specialize
    -1.64
    clinical
    -1.60
    ondo
    -1.59
    POSITIVE LOGITS
     sooner
    3.37
     lately
    3.04
     yesterday
    2.87
    ovember
    2.67
     until
    2.66
     sometime
    2.63
    until
    2.61
     awhile
    2.59
    nesday
    2.58
    aturday
    2.48
    Activations Density 0.736%

    No Known Activations