© 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. 10084
    Prev
    Next
    INDEX
    Explanations

    references to dates and mentions of news organizations or media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.10
    3:0.04
    4:0.04
    5:0.06
    6:0.35
    7:0.06
    8:0.04
    9:0.04
    10:0.16
    11:0.03
    Negative Logits
    terness
    -1.68
     patience
    -1.64
     Hallow
    -1.60
     forgiveness
    -1.47
     Morty
    -1.38
    iveness
    -1.37
    owship
    -1.34
    hett
    -1.33
     Loving
    -1.33
     Osw
    -1.31
    POSITIVE LOGITS
    vertisement
    1.49
    uthor
    1.49
    ument
    1.44
     remnants
    1.44
    wire
    1.42
    士
    1.40
     breaches
    1.39
     logos
    1.38
    ドラゴン
    1.37
    ANA
    1.36
    Activations Density 0.001%

    No Known Activations