Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 7752
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or indecision

    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
    0:0.05
    1:0.02
    2:0.04
    3:0.05
    4:0.05
    5:0.04
    6:0.20
    7:0.05
    8:0.09
    9:0.29
    10:0.04
    11:0.02
    Negative Logits
     sor
    -4.26
     Scor
    -3.55
     SQL
    -3.43
    sql
    -3.41
     Ruby
    -3.35
     Spears
    -3.23
     Pyramid
    -3.20
    py
    -3.17
    SQL
    -3.17
     Pyr
    -3.16
    POSITIVE LOGITS
     Holland
    9.27
    Dutch
    7.65
     Dutch
    7.54
     Netherlands
    7.46
     Amsterdam
    7.33
     Hague
    5.76
    sterdam
    4.94
    ijn
    4.91
     Ajax
    4.55
    ijk
    4.42
    Activations Density 0.004%

    No Known Activations