© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15491
    Prev
    Next
    INDEX
    Explanations

    notes of uncertainty or qualifiers related to varying scenarios

    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
    0:0.02
    1:0.02
    2:0.03
    3:0.04
    4:0.07
    5:0.56
    6:0.02
    7:0.02
    8:0.01
    9:0.11
    10:0.02
    11:0.03
    Negative Logits
     ))
    -3.43
    today
    -3.29
     )
    -2.93
     Lastly
    -2.91
     ).
    -2.89
     HERE
    -2.75
     Flavoring
    -2.70
    !).
    -2.67
    !
    -2.66
    Lastly
    -2.64
    POSITIVE LOGITS
     seeming
    4.61
     seemed
    4.53
     seem
    4.52
     seems
    4.09
     appears
    3.79
     appear
    3.74
    SPONSORED
    3.73
     seemingly
    3.70
     glance
    3.62
    perhaps
    3.60
    Activations Density 0.325%

    No Known Activations