© 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. 29062
    Prev
    Next
    INDEX
    Explanations

    references to coaching positions and coaching-related terms in sports

    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
    0:0.04
    1:0.01
    2:0.07
    3:0.05
    4:0.04
    5:0.08
    6:0.05
    7:0.04
    8:0.08
    9:0.07
    10:0.13
    11:0.28
    Negative Logits
     scr
    -1.65
     Krug
    -1.57
     clubhouse
    -1.54
     barracks
    -1.47
     dull
    -1.37
    �
    -1.36
    Training
    -1.35
    ��
    -1.34
     discipline
    -1.33
     lect
    -1.33
    POSITIVE LOGITS
    rencies
    1.55
    daughter
    1.51
    urrencies
    1.49
     separately
    1.43
    govtrack
    1.38
    mercial
    1.36
    Bitcoin
    1.36
    ixt
    1.36
    ileaks
    1.36
     Lyft
    1.34
    Activations Density 0.036%

    No Known Activations