© 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. 13973
    Prev
    Next
    INDEX
    Explanations

    punctuation and transitional phrases

    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
    0:0.13
    1:0.13
    2:0.09
    3:0.17
    4:0.04
    5:0.01
    6:0.09
    7:0.07
    8:0.03
    9:0.03
    10:0.10
    11:0.06
    Negative Logits
     dens
    -2.69
    Bird
    -2.66
     cellul
    -2.65
     Robbins
    -2.64
    Bee
    -2.57
     Kid
    -2.51
     stud
    -2.46
    Cell
    -2.40
     impedance
    -2.39
    ibl
    -2.38
    POSITIVE LOGITS
     UTC
    7.69
    UTC
    5.88
     GMT
    4.95
     CST
    4.33
     PDT
    4.17
    GMT
    4.00
     PST
    3.90
     CET
    3.62
     BST
    3.58
    �
    3.57
    Activations Density 0.000%

    No Known Activations