© 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. 10629
    Prev
    Next
    INDEX
    Explanations

    references to veterans and their issues with government services and support

    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
    0:0.21
    1:0.06
    2:0.04
    3:0.11
    4:0.07
    5:0.01
    6:0.16
    7:0.09
    8:0.01
    9:0.03
    10:0.09
    11:0.05
    Negative Logits
     Galileo
    -3.63
     techno
    -3.15
     lapt
    -3.14
    jab
    -3.10
     remix
    -3.09
     Gaia
    -3.06
     meteor
    -3.05
     DJs
    -3.05
     Cosmos
    -3.03
     ECB
    -2.99
    POSITIVE LOGITS
     Veterans
    8.39
     VA
    7.67
    Veter
    7.45
     veterans
    7.42
     vets
    7.33
     Veteran
    6.96
     vet
    5.60
    VA
    5.53
     Vet
    5.40
     veteran
    5.25
    Activations Density 0.091%

    No Known Activations