© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-ATT-KK
    11. 21645
    Prev
    Next
    INDEX
    Explanations

    phrases related to pressure and the psychological challenges faced by teams in competitive sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.02
    2:0.06
    3:0.07
    4:0.02
    5:0.05
    6:0.08
    7:0.05
    8:0.39
    9:0.06
    10:0.03
    11:0.03
    Negative Logits
     Vermont
    -4.22
     Rhode
    -3.89
     Ulster
    -3.84
    Ireland
    -3.61
     rugby
    -3.56
    uckland
    -3.55
     Buddha
    -3.49
     Burlington
    -3.48
    iu
    -3.45
    ijn
    -3.38
    POSITIVE LOGITS
     Astros
    8.62
     Houston
    5.64
    Houston
    5.37
     Astro
    4.76
     Rockets
    4.66
     Corpus
    4.47
    ouston
    4.33
     HOU
    4.30
     AL
    4.18
     Carlos
    4.14
    Activations Density 0.012%

    No Known Activations