© 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. 9981
    Prev
    Next
    INDEX
    Explanations

    recipes that are easy to make and utilize common ingredients

    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
    0:0.24
    1:0.01
    2:0.16
    3:0.14
    4:0.04
    5:0.10
    6:0.03
    7:0.07
    8:0.06
    9:0.03
    10:0.04
    11:0.03
    Negative Logits
    vernment
    -2.78
     Activision
    -2.67
    rift
    -2.47
    tele
    -2.42
     debugger
    -2.36
    aspers
    -2.31
     tele
    -2.27
     telecommunications
    -2.21
     Gamergate
    -2.21
     whistlebl
    -2.17
    POSITIVE LOGITS
     Recipe
    4.94
     recipe
    4.79
     Ingredients
    4.76
    Recipe
    4.67
     recipes
    4.58
     Recipes
    4.45
    Ingredients
    4.42
     Vegan
    4.17
     ingredients
    4.17
    redients
    4.10
    Activations Density 0.381%

    No Known Activations