© 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. 19328
    Prev
    Next
    INDEX
    Explanations

    references to food and eating habits

    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
    0:0.11
    1:0.03
    2:0.09
    3:0.17
    4:0.05
    5:0.25
    6:0.03
    7:0.08
    8:0.04
    9:0.02
    10:0.07
    11:0.03
    Negative Logits
     warehouses
    -2.15
     manufactures
    -2.11
     manufacturing
    -2.06
     factories
    -2.03
    rupulous
    -2.03
     suppliers
    -2.00
    stores
    -1.99
     manufacture
    -1.94
    artifacts
    -1.94
     warehouse
    -1.88
    POSITIVE LOGITS
     Fenrir
    2.03
     Gerry
    1.95
     Sturgeon
    1.87
     partisan
    1.84
    ndum
    1.79
     punt
    1.75
     Blitz
    1.73
     Messi
    1.69
     congratulations
    1.67
     Rove
    1.65
    Activations Density 0.625%

    No Known Activations