© 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. 3-ATT-KK
    11. 5479
    Prev
    Next
    INDEX
    Explanations

    elements related to health, well-being, and investigative contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.01
    1:0.05
    2:0.15
    3:0.06
    4:0.02
    5:0.07
    6:0.10
    7:0.07
    8:0.11
    9:0.14
    10:0.11
    11:0.06
    Negative Logits
    iosyncr
    -0.97
    ives
    -0.95
    uckles
    -0.93
    ividual
    -0.92
    ennett
    -0.88
    ansky
    -0.88
    veland
    -0.88
    oggles
    -0.86
     TBD
    -0.83
    iku
    -0.83
    POSITIVE LOGITS
     beforehand
    0.92
    sis
    0.86
     hitherto
    0.84
     previous
    0.82
     yesterday
    0.82
    quit
    0.81
     civilisation
    0.81
     earlier
    0.80
    croft
    0.80
    sembly
    0.79
    Activations Density 0.378%

    No Known Activations