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. 7686
    Prev
    Next
    INDEX
    Explanations

    details related to automotive specifications and performance attributes

    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
    0:0.34
    1:0.02
    2:0.07
    3:0.11
    4:0.04
    5:0.05
    6:0.06
    7:0.06
    8:0.09
    9:0.05
    10:0.04
    11:0.03
    Negative Logits
     Apache
    -2.42
    SourceFile
    -2.33
     Fitz
    -2.31
     Tavern
    -2.31
     Faul
    -2.29
    andestine
    -2.24
     balcony
    -2.24
     IPA
    -2.23
    racuse
    -2.23
     Cemetery
    -2.22
    POSITIVE LOGITS
     wheels
    4.67
     wheel
    4.62
     axle
    4.07
    wheel
    4.06
     Wheels
    4.05
     Wheel
    3.89
     spokes
    3.54
     gears
    3.38
     pedals
    3.29
    Wheel
    3.24
    Activations Density 0.013%

    No Known Activations