© 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. 27832
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to opportunities, performance assessment, and player potential in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.02
    2:0.12
    3:0.18
    4:0.13
    5:0.02
    6:0.02
    7:0.07
    8:0.04
    9:0.05
    10:0.16
    11:0.11
    Negative Logits
    ongs
    -1.36
     excerpt
    -1.36
     redacted
    -1.22
    burning
    -1.19
    cerpt
    -1.19
    express
    -1.19
    ird
    -1.18
    txt
    -1.16
     Plaint
    -1.16
    ighed
    -1.15
    POSITIVE LOGITS
     someday
    2.39
     anytime
    1.93
     tomorrow
    1.93
     sooner
    1.72
     ASAP
    1.71
     future
    1.63
     next
    1.45
     rookie
    1.45
     forever
    1.45
    iership
    1.44
    Activations Density 0.526%

    No Known Activations