© 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. 9125
    Prev
    Next
    INDEX
    Explanations

    phrases that imply evaluation and description, especially related to weaknesses in a performance or quality context

    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
    0:0.04
    1:0.07
    2:0.06
    3:0.07
    4:0.12
    5:0.16
    6:0.04
    7:0.09
    8:0.06
    9:0.14
    10:0.04
    11:0.06
    Negative Logits
    !'"
    -3.14
    م
    -2.90
    ?!"
    -2.69
     و
    -2.65
    !",
    -2.64
    ا
    -2.64
    "],"
    -2.57
    ',"
    -2.49
    ن
    -2.48
    ?'"
    -2.47
    POSITIVE LOGITS
     wears
    3.63
     Needs
    3.50
     Gets
    3.48
     lacks
    3.34
     tends
    3.19
     Poor
    3.19
     Somew
    3.00
     Causes
    2.99
     Weak
    2.94
     Moderate
    2.93
    Activations Density 0.003%

    No Known Activations