© 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. 14062
    Prev
    Next
    INDEX
    Explanations

    monetary values and references to sports transfers

    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
    0:0.14
    1:0.13
    2:0.08
    3:0.06
    4:0.05
    5:0.06
    6:0.08
    7:0.07
    8:0.04
    9:0.06
    10:0.13
    11:0.06
    Negative Logits
     bul
    -2.86
     Sheila
    -2.85
     BW
    -2.63
     Hutch
    -2.55
     buckle
    -2.51
     needles
    -2.46
     BCE
    -2.45
     Armageddon
    -2.45
     Bits
    -2.42
     Molly
    -2.41
    POSITIVE LOGITS
     Remy
    7.85
     Monaco
    3.47
     Riy
    3.46
     Nou
    3.43
    omez
    3.41
    emort
    3.41
     Raphael
    3.39
     Ras
    3.39
     Gou
    3.30
    raq
    3.27
    Activations Density 0.001%

    No Known Activations