© 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. 6542
    Prev
    Next
    INDEX
    Explanations

    references to economic factors and fiscal policies related to taxation and benefits

    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
    0:0.07
    1:0.03
    2:0.07
    3:0.28
    4:0.02
    5:0.10
    6:0.01
    7:0.06
    8:0.05
    9:0.02
    10:0.21
    11:0.03
    Negative Logits
     convinc
    -2.19
     Despair
    -2.06
     eloqu
    -2.03
    isively
    -1.99
    oliath
    -1.95
     resembled
    -1.93
    pires
    -1.93
    izont
    -1.93
    ernaut
    -1.91
    onica
    -1.91
    POSITIVE LOGITS
     expenses
    3.56
     reimburse
    3.52
     fees
    3.15
     payments
    3.13
     reimbursement
    3.12
     vacations
    3.06
     expenditures
    3.06
     warranties
    3.01
     emergencies
    2.99
     supplemental
    2.95
    Activations Density 0.208%

    No Known Activations