© 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. 30253
    Prev
    Next
    INDEX
    Explanations

    phrases and references related to Edward Snowden and his actions regarding NSA leaks and surveillance

    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
    0:0.02
    1:0.01
    2:0.05
    3:0.06
    4:0.05
    5:0.02
    6:0.03
    7:0.03
    8:0.02
    9:0.04
    10:0.43
    11:0.18
    Negative Logits
     Orn
    -1.58
    SourceFile
    -1.55
     Corpus
    -1.46
     precincts
    -1.41
    emonium
    -1.41
     Marketable
    -1.40
     subdivision
    -1.39
     voic
    -1.32
     Norm
    -1.32
    seless
    -1.32
    POSITIVE LOGITS
    kies
    1.68
    soon
    1.65
    ierra
    1.57
    ovych
    1.56
    iday
    1.55
    jet
    1.52
    uador
    1.50
    igrated
    1.48
     breakout
    1.44
    ierre
    1.44
    Activations Density 0.019%

    No Known Activations