© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 34014
    Prev
    Next
    INDEX
    Explanations

    numerical data related to dates, monetary values, and percentages in financial or statistical contexts

    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
    0:0.23
    1:0.07
    2:0.07
    3:0.08
    4:0.03
    5:0.05
    6:0.02
    7:0.02
    8:0.05
    9:0.18
    10:0.06
    11:0.08
    Negative Logits
    DragonMagazine
    -1.76
    [/
    -1.64
    "},"
    -1.56
    Footnote
    -1.54
     Sturgeon
    -1.50
    anos
    -1.50
     sclerosis
    -1.48
    obal
    -1.45
    の�
    -1.44
    conservancy
    -1.43
    POSITIVE LOGITS
    lap
    1.46
    inct
    1.45
     tuning
    1.39
     cheering
    1.36
    iday
    1.34
    secut
    1.31
     satir
    1.29
     silence
    1.27
     apple
    1.27
    plates
    1.27
    Activations Density 0.081%

    No Known Activations