© 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. 10900
    Prev
    Next
    INDEX
    Explanations

    references to banking institutions and related operations

    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
    0:0.08
    1:0.07
    2:0.09
    3:0.04
    4:0.07
    5:0.02
    6:0.15
    7:0.16
    8:0.02
    9:0.05
    10:0.14
    11:0.07
    Negative Logits
     lett
    -2.59
     Schumer
    -2.42
     admissions
    -2.37
     coh
    -2.36
     squats
    -2.30
     Huff
    -2.29
     dumps
    -2.28
     schools
    -2.27
     quotas
    -2.27
     regist
    -2.26
    POSITIVE LOGITS
     Bank
    4.07
    Bank
    3.78
     Highlights
    3.00
    wcsstore
    2.80
    ��
    2.72
    aukee
    2.67
    ":["
    2.65
     IMAGES
    2.51
    BIL
    2.50
    amina
    2.47
    Activations Density 0.004%

    No Known Activations