© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-ATT-KK
    11. 9709
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the taste and quality of food, particularly desserts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.04
    2:0.07
    3:0.09
    4:0.04
    5:0.07
    6:0.08
    7:0.22
    8:0.05
    9:0.04
    10:0.08
    11:0.14
    Negative Logits
    etsk
    -1.41
    usted
    -1.26
    ayne
    -1.22
    axter
    -1.21
    Browser
    -1.21
     Telecommunications
    -1.21
    oute
    -1.17
    pload
    -1.14
    iden
    -1.13
     CIS
    -1.11
    POSITIVE LOGITS
    Ingredients
    1.62
     tastes
    1.59
     Grape
    1.52
     fru
    1.48
     cuisine
    1.47
     Recipes
    1.46
     Delicious
    1.45
     wines
    1.44
     cher
    1.42
     grapes
    1.42
    Activations Density 0.012%

    No Known Activations