© 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. 10608
    Prev
    Next
    INDEX
    Explanations

    references to social and community-related issues or events

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.03
    1:0.01
    2:0.06
    3:0.04
    4:0.05
    5:0.29
    6:0.02
    7:0.03
    8:0.01
    9:0.26
    10:0.01
    11:0.12
    Negative Logits
    pires
    -2.70
     combines
    -2.52
     faithfully
    -2.49
    soever
    -2.37
    until
    -2.31
     excel
    -2.31
    semble
    -2.30
    olutely
    -2.26
     ensures
    -2.24
    brates
    -2.24
    POSITIVE LOGITS
    being
    3.66
     being
    3.65
     disappearing
    3.26
     leaking
    3.24
     questioning
    3.20
     needing
    3.20
     hurting
    3.07
     tampering
    3.02
     cance
    2.99
     slipping
    2.96
    Activations Density 0.432%

    No Known Activations