© 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. 9-ATT-KK
    11. 8885
    Prev
    Next
    INDEX
    Explanations

    concepts related to energy balance and dietary effects

    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
    0:0.05
    1:0.02
    2:0.10
    3:0.40
    4:0.03
    5:0.09
    6:0.02
    7:0.06
    8:0.04
    9:0.03
    10:0.06
    11:0.04
    Negative Logits
    gallery
    -2.09
    Deal
    -2.09
     Dollars
    -2.07
     Cheap
    -1.88
     Blog
    -1.86
     Advocate
    -1.86
    wered
    -1.86
    Books
    -1.84
     Wiz
    -1.84
    Company
    -1.83
    POSITIVE LOGITS
     morphology
    3.14
     susceptibility
    3.01
     phenotype
    2.95
     microbial
    2.92
     circadian
    2.87
     variability
    2.85
     endogenous
    2.85
     physiological
    2.81
     atten
    2.78
     decay
    2.73
    Activations Density 1.300%

    No Known Activations