© 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. 15943
    Prev
    Next
    INDEX
    Explanations

    terms related to sports history and statistics

    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
    2:0.11
    3:0.48
    4:0.09
    5:0.08
    6:0.01
    7:0.05
    8:0.03
    9:0.05
    10:0.01
    11:0.01
    Negative Logits
     
    -6.09
    --
    -5.86
    ``
    -5.86
      
    -5.33
       
    -5.14
    )--
    -4.92
    ".[
    -4.71
    -->
    -4.48
     ``
    -4.47
    ````
    -4.38
    POSITIVE LOGITS
     —
    9.60
     ­
    5.00
    ­
    4.92
     ―
    4.92
     …
    4.79
     pic
    4.51
     »
    4.03
    Enlarge
    3.79
     McMaster
    3.65
     POLITICO
    3.60
    Activations Density 0.958%

    No Known Activations