© 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. 5-ATT-KK
    11. 10222
    Prev
    Next
    INDEX
    Explanations

    references to wealth and financial status

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.01
    1:0.00
    2:0.19
    3:0.16
    4:0.16
    5:0.03
    6:0.02
    7:0.06
    8:0.08
    9:0.05
    10:0.11
    11:0.07
    Negative Logits
    ophon
    -1.78
    aptic
    -1.73
    ggles
    -1.65
    arger
    -1.64
    ibaba
    -1.62
    quartered
    -1.62
    asive
    -1.61
    eeper
    -1.59
    ertain
    -1.59
    ramer
    -1.57
    POSITIVE LOGITS
    didn
    2.20
     yesterday
    2.01
     didnt
    2.01
     Didn
    1.90
     wrong
    1.82
    terday
    1.82
     failed
    1.79
     bailed
    1.77
     didn
    1.74
     incompet
    1.70
    Activations Density 0.352%

    No Known Activations