© 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. 46704
    Prev
    Next
    INDEX
    Explanations

    references to team groups and their standings in a sports tournament

    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
    0:0.04
    1:0.02
    2:0.08
    3:0.06
    4:0.06
    5:0.04
    6:0.11
    7:0.14
    8:0.04
    9:0.04
    10:0.24
    11:0.06
    Negative Logits
    RIP
    -1.72
    lar
    -1.63
    ifix
    -1.49
    uti
    -1.47
    ukong
    -1.44
     effic
    -1.43
    mpeg
    -1.43
    oldown
    -1.42
     Metatron
    -1.41
     Revelations
    -1.40
    POSITIVE LOGITS
     standings
    1.88
     grouping
    1.88
     relegation
    1.83
     qualifiers
    1.82
    roups
    1.77
    actionDate
    1.66
     pitted
    1.62
     positional
    1.61
    GROUP
    1.58
    inational
    1.57
    Activations Density 0.002%

    No Known Activations