© 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. 8389
    Prev
    Next
    INDEX
    Explanations

    punctuations and their relationships to sentences in the text

    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
    0:0.18
    1:0.13
    2:0.05
    3:0.02
    4:0.03
    5:0.02
    6:0.13
    7:0.08
    8:0.02
    9:0.05
    10:0.21
    11:0.03
    Negative Logits
     ILCS
    -3.31
     Faul
    -3.17
     Watson
    -3.12
     transf
    -3.09
     Mau
    -3.01
    bryce
    -2.95
     Hanson
    -2.90
     Kenya
    -2.88
    wm
    -2.88
    heid
    -2.87
    POSITIVE LOGITS
     Rog
    10.03
    Rog
    7.46
     rog
    6.44
    rog
    5.66
     Rogue
    5.03
    Rogue
    4.62
     Riv
    4.13
     Sin
    3.75
     Roll
    3.73
     Rogers
    3.72
    Activations Density 0.002%

    No Known Activations