© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 16706
    Prev
    Next
    INDEX
    Explanations

    numerical values related to measurements and distances

    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
    0:0.10
    1:0.08
    2:0.07
    3:0.11
    4:0.02
    5:0.02
    6:0.07
    7:0.13
    8:0.04
    9:0.03
    10:0.16
    11:0.11
    Negative Logits
     fixtures
    -2.38
     holog
    -2.35
     REPL
    -2.25
     Phillies
    -2.24
     interns
    -2.18
     toile
    -2.13
     Spielberg
    -2.12
     printers
    -2.11
     cuff
    -2.11
     typew
    -2.10
    POSITIVE LOGITS
     km
    4.91
    km
    4.61
     kilometres
    3.78
     KM
    3.59
     kilometers
    3.58
    kil
    3.50
     kilomet
    3.49
    wy
    3.43
     mi
    2.93
     nm
    2.75
    Activations Density 0.005%

    No Known Activations