© 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. 10776
    Prev
    Next
    INDEX
    Explanations

    statistical data related to health metrics, particularly concerning abortion rates and demographic information

    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
    2:0.04
    3:0.05
    4:0.05
    5:0.12
    6:0.03
    7:0.06
    8:0.04
    9:0.32
    10:0.04
    11:0.14
    Negative Logits
     seeming
    -2.81
    comings
    -2.61
     scrambling
    -2.49
     suspending
    -2.46
     swirling
    -2.46
    blems
    -2.45
    checking
    -2.40
     inconsistencies
    -2.40
     reluct
    -2.38
     disappearing
    -2.37
    POSITIVE LOGITS
     per
    3.03
     acre
    2.97
     capita
    2.95
     hect
    2.85
     average
    2.76
     metric
    2.66
     population
    2.58
     avg
    2.52
     adult
    2.45
    average
    2.42
    Activations Density 0.014%

    No Known Activations