© 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. 21165
    Prev
    Next
    INDEX
    Explanations

    references to types of heating sources or energy alternatives

    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
    0:0.19
    1:0.25
    2:0.02
    3:0.02
    4:0.02
    5:0.03
    6:0.06
    7:0.11
    8:0.03
    9:0.03
    10:0.14
    11:0.04
    Negative Logits
     Cavs
    -3.13
     Pierce
    -3.05
     Iv
    -2.76
    Diamond
    -2.75
    NBA
    -2.72
     Emin
    -2.69
     Celtic
    -2.67
     NHL
    -2.67
     Shattered
    -2.63
    zin
    -2.62
    POSITIVE LOGITS
    ero
    5.49
    eros
    3.47
     Aero
    3.11
     Clover
    3.02
     Fu
    3.01
    ernel
    2.95
     Miko
    2.94
    iesel
    2.93
    iso
    2.90
     autop
    2.83
    Activations Density 0.001%

    No Known Activations