© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 18348
    Prev
    Next
    INDEX
    Explanations

    the presence of commas in the text

    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
    1:0.08
    2:0.08
    3:0.08
    4:0.07
    5:0.07
    6:0.09
    7:0.08
    8:0.08
    9:0.09
    10:0.06
    11:0.07
    Negative Logits
     cessation
    -3.02
    aiden
    -3.00
     intermittent
    -2.85
    ebus
    -2.81
    uchin
    -2.75
    riers
    -2.74
     carrier
    -2.73
    liction
    -2.64
     blocker
    -2.61
    uyomi
    -2.58
    POSITIVE LOGITS
     Ambro
    3.33
     Aust
    3.17
     Vintage
    3.04
     Cyr
    3.03
    CHAT
    3.00
     Armen
    2.93
    MAT
    2.92
     EDITION
    2.83
     Sed
    2.79
     LX
    2.71
    Activations Density 0.000%

    No Known Activations