© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14914
    Prev
    Next
    INDEX
    Explanations

    references to server structures and performance issues

    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
    0:0.20
    1:0.04
    2:0.06
    3:0.07
    4:0.05
    5:0.03
    6:0.22
    7:0.07
    8:0.03
    9:0.04
    10:0.04
    11:0.09
    Negative Logits
     glim
    -3.23
    Ford
    -3.12
     Ford
    -2.97
     Spiegel
    -2.95
     Pett
    -2.77
    Toy
    -2.76
     Suzuki
    -2.75
     Toy
    -2.74
     hemp
    -2.70
     Buddh
    -2.68
    POSITIVE LOGITS
     servers
    7.35
     server
    7.22
     Server
    6.94
    Server
    6.47
    server
    6.39
    erver
    4.93
     MySQL
    4.45
     Ser
    4.38
    Ser
    4.28
    ginx
    4.08
    Activations Density 0.055%

    No Known Activations