© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14595
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    0:0.08
    1:0.08
    2:0.08
    3:0.08
    4:0.08
    5:0.07
    6:0.08
    7:0.07
    8:0.08
    9:0.09
    10:0.07
    11:0.09
    Negative Logits
    Coun
    -3.14
    DragonMagazine
    -3.05
     Coun
    -2.90
     "$:/
    -2.75
     Companion
    -2.70
     [&
    -2.67
     Cust
    -2.62
     Wedding
    -2.57
     Pwr
    -2.56
     BaseType
    -2.54
    POSITIVE LOGITS
     leaps
    2.77
     pause
    2.61
    ogie
    2.51
     hoops
    2.49
     bounce
    2.46
     autos
    2.44
     blasts
    2.31
    atility
    2.27
     lung
    2.26
    smoking
    2.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.