© 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. 13418
    Prev
    Next
    INDEX
    Explanations

    concepts related to behavior and accountability in sports contexts

    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
    1:0.01
    2:0.05
    3:0.04
    4:0.07
    5:0.48
    6:0.02
    7:0.03
    8:0.02
    9:0.16
    10:0.02
    11:0.03
    Negative Logits
    orio
    -3.02
     awaited
    -2.77
     expires
    -2.61
    ADVERTISEMENT
    -2.51
     awaits
    -2.47
     transpired
    -2.43
     resides
    -2.30
     Else
    -2.29
    failed
    -2.27
    undo
    -2.27
    POSITIVE LOGITS
     fairly
    5.16
     nicely
    5.12
     quite
    5.11
     pretty
    4.95
     MUCH
    4.93
     tremendously
    4.90
     wonderfully
    4.87
     very
    4.69
     considerably
    4.67
     remarkably
    4.63
    Activations Density 0.830%

    No Known Activations