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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22905
    Prev
    Next
    INDEX
    Explanations

    recipes and cooking instructions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    recipes involving various culinary techniques and ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.30
    2:0.03
    3:0.03
    4:0.02
    5:0.04
    6:0.08
    7:0.09
    8:0.04
    9:0.04
    10:0.16
    11:0.08
    Negative Logits
     temporal
    -2.29
     unmanned
    -2.26
     Telecom
    -2.12
     seism
    -2.07
    atellite
    -2.06
     manifest
    -2.00
    href
    -2.00
     simulations
    -1.97
     RSA
    -1.89
    remote
    -1.89
    POSITIVE LOGITS
    Ingredients
    3.31
     Ingredients
    3.17
     ingredients
    3.11
    Nut
    3.00
     aroma
    2.99
     veggies
    2.93
     Nutrition
    2.93
     creamy
    2.89
     Vegan
    2.85
    Recipe
    2.77
    Activations Density 0.473%

    No Known Activations