© 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. 47258
    Prev
    Next
    INDEX
    Explanations

    mention of percentages and changes in statistical data

    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
    0:0.03
    1:0.01
    2:0.11
    3:0.04
    4:0.07
    5:0.03
    6:0.13
    7:0.28
    8:0.06
    9:0.03
    10:0.07
    11:0.08
    Negative Logits
    markets
    -1.77
    chart
    -1.67
    chool
    -1.60
    auder
    -1.46
    ashtra
    -1.44
    erto
    -1.44
     Topics
    -1.43
    udeb
    -1.40
    olis
    -1.40
    ebook
    -1.40
    POSITIVE LOGITS
     gh
    1.58
     HRC
    1.50
    lihood
    1.48
     Rez
    1.47
     handshake
    1.45
     throat
    1.41
     throats
    1.39
     idols
    1.38
     morphine
    1.38
     suicide
    1.36
    Activations Density 0.004%

    No Known Activations