© 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. 38311
    Prev
    Next
    INDEX
    Explanations

    references to social dynamics and physical attributes related to communities, including support for marginalized groups

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.01
    1:0.02
    2:0.09
    3:0.12
    4:0.38
    5:0.02
    6:0.05
    7:0.11
    8:0.03
    9:0.03
    10:0.05
    11:0.05
    Negative Logits
    evidence
    -1.82
    rek
    -1.69
    allows
    -1.63
    ibliography
    -1.60
    iesta
    -1.60
    zyme
    -1.55
    toc
    -1.52
    arthed
    -1.47
    miah
    -1.45
    lda
    -1.42
    POSITIVE LOGITS
     purposes
    1.91
     sensibilities
    1.74
     printers
    1.50
     eventual
    1.45
     whim
    1.41
     purpose
    1.41
     needs
    1.41
     pree
    1.38
     whims
    1.38
    ORPG
    1.38
    Activations Density 0.047%

    No Known Activations