© 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. 7556
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical data related to various measurements, especially in the context of public health and economics

    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
    1:0.10
    2:0.03
    3:0.04
    4:0.03
    5:0.06
    6:0.04
    7:0.33
    8:0.12
    9:0.05
    10:0.05
    11:0.04
    Negative Logits
     Nap
    -2.79
    Nap
    -2.72
     Palmer
    -2.62
    NetMessage
    -2.58
     Penal
    -2.56
     Porter
    -2.55
     Melvin
    -2.54
     notor
    -2.52
     advoc
    -2.47
     Preferred
    -2.45
    POSITIVE LOGITS
    hower
    2.94
    DW
    2.55
    sky
    2.52
     Homs
    2.50
    witz
    2.47
     Rw
    2.45
    yrinth
    2.43
    acks
    2.42
    keyes
    2.39
    ews
    2.37
    Activations Density 0.012%

    No Known Activations