© 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. 10-ATT-KK
    11. 13989
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to shooting performance in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.08
    2:0.06
    3:0.08
    4:0.10
    5:0.05
    6:0.11
    7:0.07
    8:0.06
    9:0.08
    10:0.06
    11:0.12
    Negative Logits
    actionDate
    -2.78
    atom
    -2.64
     quarantine
    -2.45
     Banking
    -2.39
     Grac
    -2.35
     +---
    -2.33
     Franç
    -2.21
     hiber
    -2.20
     Chrys
    -2.19
     Liv
    -2.19
    POSITIVE LOGITS
     percentage
    3.79
     percentages
    3.63
     turnovers
    3.50
     Percentage
    3.32
     efficiency
    3.24
     effectiveness
    3.22
     +/-
    3.22
     averages
    3.19
     scoring
    3.19
    orsi
    3.17
    Activations Density 0.101%

    No Known Activations