© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 20820
    Prev
    Next
    INDEX
    Explanations

    mentions of ownership and control regarding personal or corporate assets

    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
    1:0.07
    2:0.07
    3:0.03
    4:0.02
    5:0.02
    6:0.19
    7:0.09
    8:0.03
    9:0.03
    10:0.32
    11:0.03
    Negative Logits
    ongo
    -3.30
    \\\\\\\\\\\\\\\\
    -2.89
    ilater
    -2.86
    MT
    -2.75
    TB
    -2.74
     Pluto
    -2.63
    iband
    -2.60
    hens
    -2.54
    POR
    -2.52
    razil
    -2.50
    POSITIVE LOGITS
     Ad
    10.41
    Ad
    8.27
     ad
    7.04
    ad
    6.22
     AD
    6.01
     Ads
    5.27
     ads
    4.69
    ads
    4.59
    AD
    4.59
     advertis
    4.43
    Activations Density 0.068%

    No Known Activations