© 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. 5632
    Prev
    Next
    INDEX
    Explanations

    financial terms and statistics related to income and taxes

    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
    0:0.17
    1:0.04
    2:0.21
    3:0.10
    4:0.05
    5:0.12
    6:0.05
    7:0.06
    8:0.05
    9:0.04
    10:0.04
    11:0.03
    Negative Logits
     PCB
    -2.48
     disinfect
    -2.35
    CVE
    -2.17
    natureconservancy
    -2.16
    umbn
    -2.05
     crush
    -2.03
     Atomic
    -1.99
     recons
    -1.98
    assies
    -1.96
    UV
    -1.92
    POSITIVE LOGITS
     income
    4.27
     earners
    4.18
     incomes
    4.16
     Income
    3.93
     earnings
    3.67
    income
    3.62
     median
    3.36
     earning
    3.24
     deductions
    3.17
     salary
    3.10
    Activations Density 0.239%

    No Known Activations