Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 43669
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    5:0.08
    6:0.07
    7:0.08
    8:0.08
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
    CLASS
    -1.94
    leep
    -1.92
    kids
    -1.88
    iverse
    -1.88
    externalActionCode
    -1.83
    LO
    -1.78
    married
    -1.78
    ocene
    -1.75
    scient
    -1.74
     HAVE
    -1.73
    POSITIVE LOGITS
     Sparks
    1.79
     Gol
    1.73
     Kris
    1.70
     Schro
    1.69
     Arche
    1.66
     Tur
    1.66
     Ratt
    1.62
     Ivan
    1.62
     hybrids
    1.61
     Amon
    1.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.