© 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. 5-ATT-KK
    11. 43903
    Prev
    Next
    INDEX
    Explanations

    important concepts and elements related to sports and competitive environments

    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
    0:0.02
    1:0.03
    2:0.09
    3:0.07
    4:0.07
    5:0.04
    6:0.39
    7:0.02
    8:0.04
    9:0.05
    10:0.08
    11:0.05
    Negative Logits
     oneself
    -1.73
     weap
    -1.41
    alach
    -1.35
    ividually
    -1.30
    rarily
    -1.29
     awhile
    -1.26
     contro
    -1.24
     las
    -1.21
     cig
    -1.21
    ankind
    -1.20
    POSITIVE LOGITS
    Stat
    1.49
    flags
    1.33
    latest
    1.27
    udeb
    1.16
    abol
    1.14
    venth
    1.13
     Wilkinson
    1.12
    irements
    1.11
    angu
    1.09
    editor
    1.08
    Activations Density 0.123%

    No Known Activations