© 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. 10-ATT-KK
    11. 20211
    Prev
    Next
    INDEX
    Explanations

    metrics and statistics related to rankings and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.03
    2:0.03
    3:0.44
    4:0.04
    5:0.03
    6:0.06
    7:0.09
    8:0.03
    9:0.04
    10:0.03
    11:0.08
    Negative Logits
    ──
    -2.37
     realise
    -2.35
    founded
    -2.32
     Died
    -2.13
     extant
    -2.13
    regation
    -2.12
    asio
    -2.11
     descendants
    -2.11
    aughtered
    -2.09
    ".[
    -2.08
    POSITIVE LOGITS
     week
    6.35
    Week
    6.28
     Week
    5.90
    week
    5.53
     weekly
    5.51
     fortnight
    5.10
     weekend
    5.07
     WEEK
    5.03
     weeks
    4.97
     Mondays
    4.94
    Activations Density 0.167%

    No Known Activations