© 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. 39736
    Prev
    Next
    INDEX
    Explanations

    indicators of product quality and performance

    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
    2:0.11
    3:0.49
    4:0.07
    5:0.02
    6:0.02
    7:0.03
    8:0.05
    9:0.03
    10:0.04
    11:0.05
    Negative Logits
    thia
    -2.15
    ctuary
    -1.90
    anwhile
    -1.85
    ngth
    -1.74
     HELP
    -1.69
    IRT
    -1.65
    }.
    -1.65
    HC
    -1.62
    .�
    -1.62
    .''.
    -1.60
    POSITIVE LOGITS
    essen
    1.83
    ?),
    1.71
     due
    1.70
     technically
    1.67
    ?,
    1.59
     outright
    1.59
     (),
    1.56
     mete
    1.56
     FSA
    1.55
     deriv
    1.52
    Activations Density 0.768%

    No Known Activations