© 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. 9-ATT-KK
    11. 23891
    Prev
    Next
    INDEX
    Explanations

    references to the Quran

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.08
    2:0.07
    3:0.09
    4:0.07
    5:0.07
    6:0.10
    7:0.09
    8:0.08
    9:0.08
    10:0.07
    11:0.07
    Negative Logits
    Magikarp
    -3.68
    MIT
    -3.35
     Ng
    -3.25
    Gil
    -2.91
    ゴン
    -2.90
    Gy
    -2.83
    536
    -2.81
    Lim
    -2.80
    mson
    -2.77
    Score
    -2.73
    POSITIVE LOGITS
     tutorials
    2.78
     sewing
    2.77
     recept
    2.69
     containers
    2.66
     blister
    2.57
     roller
    2.55
     corners
    2.54
     gatherings
    2.53
    verend
    2.52
    reet
    2.51
    Activations Density 0.000%

    No Known Activations