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. 43792
    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
    1:0.07
    2:0.09
    3:0.09
    4:0.08
    5:0.08
    6:0.09
    7:0.08
    8:0.08
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
    estamp
    -1.95
    ffiti
    -1.87
    sembly
    -1.86
    ontent
    -1.86
    enhagen
    -1.80
    astery
    -1.79
    section
    -1.77
    posium
    -1.75
    rollment
    -1.74
    posal
    -1.73
    POSITIVE LOGITS
     mathematician
    1.80
     chromos
    1.70
     autonomy
    1.66
     germ
    1.66
     grief
    1.64
     bere
    1.60
     vaccine
    1.57
     gravity
    1.57
     charact
    1.57
     tragedies
    1.55
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.