© 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. 5-ATT-KK
    11. 45431
    Prev
    Next
    INDEX
    Explanations

    words related to team sports and tournament structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.16
    2:0.02
    3:0.04
    4:0.02
    5:0.31
    6:0.02
    7:0.01
    8:0.05
    9:0.12
    10:0.07
    11:0.03
    Negative Logits
     ecosystem
    -1.48
     cryptoc
    -1.43
     airs
    -1.43
     commod
    -1.41
     organising
    -1.40
     PRES
    -1.39
     paws
    -1.38
     fundament
    -1.38
     ecosystems
    -1.37
     QUEST
    -1.35
    POSITIVE LOGITS
    erion
    1.93
    lda
    1.89
    ucket
    1.81
    raltar
    1.79
    anan
    1.77
    layer
    1.71
    ylon
    1.63
    ector
    1.63
    enza
    1.61
    auga
    1.60
    Activations Density 0.456%

    No Known Activations