© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 449
    Prev
    Next
    INDEX
    Explanations

    references to national debt and its implications

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.01
    2:0.39
    3:0.07
    4:0.03
    5:0.07
    6:0.05
    7:0.05
    8:0.09
    9:0.04
    10:0.03
    11:0.02
    Negative Logits
    Hunt
    -2.96
     Beir
    -2.87
     scouting
    -2.79
     sighting
    -2.67
     mosqu
    -2.64
     Selection
    -2.54
    Preview
    -2.53
     homophobic
    -2.52
     selections
    -2.50
     sightings
    -2.49
    POSITIVE LOGITS
     Debt
    6.80
     debt
    6.46
     debts
    5.83
     debtor
    5.58
     creditors
    5.06
     repayment
    4.89
     creditor
    4.78
     bankruptcy
    4.77
    ebted
    4.66
     bankrupt
    4.63
    Activations Density 0.206%

    No Known Activations