© 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. 17219
    Prev
    Next
    INDEX
    Explanations

    discussions about government policies and their impact on personal freedoms

    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
    0:0.05
    1:0.05
    2:0.04
    3:0.09
    4:0.04
    5:0.01
    6:0.36
    7:0.12
    8:0.02
    9:0.04
    10:0.03
    11:0.08
    Negative Logits
     Deck
    -2.93
    Raven
    -2.74
    runner
    -2.62
    ritch
    -2.41
    etter
    -2.40
    deck
    -2.38
    SIGN
    -2.36
     Contribut
    -2.35
    RAFT
    -2.34
    apper
    -2.33
    POSITIVE LOGITS
     government
    7.82
    Government
    7.47
    government
    7.10
     Government
    6.50
     governments
    5.93
     governmental
    5.65
     Governments
    5.25
     ministries
    5.15
     bureaucrats
    4.85
    gov
    4.82
    Activations Density 0.522%

    No Known Activations