© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 42538
    Prev
    Next
    INDEX
    Explanations

    numerical values and rankings related to sports teams or statistical data

    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
    0:0.10
    1:0.07
    2:0.14
    3:0.09
    4:0.09
    5:0.06
    6:0.17
    7:0.01
    8:0.04
    9:0.07
    10:0.05
    11:0.05
    Negative Logits
    soDeliveryDate
    -1.51
    aceutical
    -1.36
    mbudsman
    -1.33
    gmail
    -1.28
    Fla
    -1.27
     Newsletter
    -1.25
    ":["
    -1.23
     Grail
    -1.22
     Archdemon
    -1.21
     Thousand
    -1.21
    POSITIVE LOGITS
     snag
    1.29
     grunt
    1.27
    itud
    1.27
     seiz
    1.26
    \":
    1.25
     elim
    1.21
    arial
    1.21
     admissions
    1.21
    onal
    1.18
     +++
    1.17
    Activations Density 0.014%

    No Known Activations