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

    Neuronpedia

    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. 15406
    Prev
    Next
    INDEX
    Explanations

    elements related to product features and improvements

    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
    0:0.07
    1:0.34
    2:0.06
    3:0.04
    4:0.06
    5:0.02
    6:0.05
    7:0.10
    8:0.02
    9:0.03
    10:0.09
    11:0.06
    Negative Logits
    �
    -2.94
     disembark
    -2.54
     Ryder
    -2.52
    uez
    -2.52
     grandparents
    -2.46
    rompt
    -2.44
    alle
    -2.42
     Entry
    -2.40
    vernment
    -2.34
    ylum
    -2.33
    POSITIVE LOGITS
     thin
    7.38
     Thin
    7.17
    thin
    6.81
     thinner
    6.52
     thick
    5.44
     thicker
    5.33
     Thick
    5.27
     thickness
    5.02
     slim
    4.28
     slender
    3.97
    Activations Density 0.019%

    No Known Activations