© 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. 17435
    Prev
    Next
    INDEX
    Explanations

    connections to Massachusetts and its various programs and policies

    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
    0:0.21
    1:0.03
    2:0.03
    3:0.07
    4:0.03
    5:0.02
    6:0.10
    7:0.15
    8:0.01
    9:0.03
    10:0.23
    11:0.03
    Negative Logits
    Turkey
    -3.79
     Croatian
    -3.75
     Azerbai
    -3.64
     Sloven
    -3.63
     Azerbaijan
    -3.57
     Armenia
    -3.52
    Turkish
    -3.50
     Croatia
    -3.46
     Cherokee
    -3.40
     Turkey
    -3.38
    POSITIVE LOGITS
     Massachusetts
    5.63
     Worcester
    5.05
    Mass
    4.62
     Mass
    4.26
    achusetts
    4.02
     Lowell
    3.85
     MA
    3.81
     Middles
    3.70
     Boston
    3.58
    Boston
    3.53
    Activations Density 0.016%

    No Known Activations