© 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. 10-ATT-KK
    11. 20863
    Prev
    Next
    INDEX
    Explanations

    topics related to education and adolescent health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.12
    2:0.15
    3:0.08
    4:0.04
    5:0.02
    6:0.11
    7:0.17
    8:0.01
    9:0.03
    10:0.07
    11:0.05
    Negative Logits
     Lenin
    -2.09
     Corbyn
    -2.06
     Frazier
    -2.00
    TRUMP
    -1.95
     Hol
    -1.90
    Lenin
    -1.86
     Pod
    -1.85
    atorial
    -1.85
     scept
    -1.84
    の�
    -1.84
    POSITIVE LOGITS
     teen
    4.90
     teens
    4.77
    Teen
    4.66
     Teen
    4.51
     teenagers
    3.96
     teenage
    3.93
     adolesc
    3.71
    olesc
    3.58
     adolescents
    3.57
     adolescent
    3.55
    Activations Density 0.046%

    No Known Activations