© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 21886
    Prev
    Next
    INDEX
    Explanations

    numbers and statistics related to sports team performance

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    Head Attr Weights
    0:0.19
    1:0.12
    2:0.14
    3:0.06
    4:0.04
    5:0.09
    6:0.03
    7:0.02
    8:0.07
    9:0.10
    10:0.04
    11:0.06
    Negative Logits
    quart
    -1.45
    lished
    -1.43
     Quote
    -1.39
    raints
    -1.27
     Rider
    -1.27
     CrossRef
    -1.27
    entary
    -1.25
    liest
    -1.25
    EngineDebug
    -1.24
    DragonMagazine
    -1.24
    POSITIVE LOGITS
     recycle
    1.22
    isans
    1.21
     defer
    1.11
     halted
    1.11
    imize
    1.09
     trickle
    1.08
     handic
    1.08
     brush
    1.08
     erase
    1.06
    �
    1.05
    Activations Density 0.040%

    No Known Activations