© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 18941
    Prev
    Next
    INDEX
    Explanations

    discussions related to the health impacts of sugar consumption and its influence on dietary guidelines

    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
    0:0.15
    1:0.02
    2:0.14
    3:0.08
    4:0.05
    5:0.08
    6:0.09
    7:0.07
    8:0.14
    9:0.06
    10:0.02
    11:0.03
    Negative Logits
    etsk
    -3.27
     Clockwork
    -3.10
     Mak
    -3.05
     Mehran
    -3.03
     Shant
    -2.99
    Camera
    -2.96
     Logan
    -2.92
    atown
    -2.92
     Arkham
    -2.89
     Tatt
    -2.88
    POSITIVE LOGITS
     fructose
    6.27
     sugar
    6.13
     sugars
    5.84
     Sugar
    5.77
    ructose
    5.21
     suc
    4.81
     sweetness
    4.77
     glucose
    4.60
    ugar
    4.23
     Sug
    4.14
    Activations Density 0.022%

    No Known Activations