© 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. 19965
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting symbols

    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
    0:0.09
    1:0.02
    2:0.05
    3:0.03
    4:0.05
    5:0.03
    6:0.19
    7:0.04
    8:0.05
    9:0.33
    10:0.02
    11:0.04
    Negative Logits
    rir
    -4.04
    sembly
    -3.52
    hower
    -3.52
    negie
    -3.28
    iola
    -3.28
     SAR
    -3.28
     Ruler
    -3.27
     Gir
    -3.27
     sage
    -3.21
    vir
    -3.20
    POSITIVE LOGITS
    Matt
    9.21
     Matt
    9.13
     matt
    7.00
     mattress
    5.34
     Mattis
    5.11
     Matthew
    4.70
     Duff
    4.69
    Matthew
    4.51
     Madd
    4.39
     Daredevil
    4.20
    Activations Density 0.013%

    No Known Activations