© 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. 9-ATT-KK
    11. 20944
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.03
    2:0.06
    3:0.04
    4:0.06
    5:0.04
    6:0.29
    7:0.04
    8:0.05
    9:0.21
    10:0.03
    11:0.02
    Negative Logits
    feld
    -3.82
    iott
    -3.71
    agos
    -3.71
    arella
    -3.61
     Doyle
    -3.41
     Elliott
    -3.39
    glers
    -3.36
     Feder
    -3.34
    artisan
    -3.26
    illus
    -3.24
    POSITIVE LOGITS
     Sun
    8.97
    Sun
    8.92
    sun
    8.39
     sun
    8.09
     SUN
    7.16
     sunscreen
    6.46
     Sunrise
    6.04
     Sunny
    5.57
     Sunshine
    5.24
     sunshine
    5.24
    Activations Density 0.018%

    No Known Activations