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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 44198
    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
    0:0.07
    1:0.11
    2:0.07
    3:0.08
    4:0.07
    5:0.08
    6:0.08
    7:0.07
    8:0.08
    9:0.07
    10:0.08
    11:0.08
    Negative Logits
     therap
    -2.08
     toget
    -2.00
    sbm
    -1.98
     rul
    -1.93
    escape
    -1.93
     Ukrain
    -1.91
    anta
    -1.90
    ocent
    -1.90
    isites
    -1.88
    emis
    -1.85
    POSITIVE LOGITS
     Kop
    1.83
     BlackBerry
    1.73
     Scroll
    1.71
     iPod
    1.70
     throughput
    1.62
     Ethernet
    1.56
     corridor
    1.56
     Albion
    1.54
    �醒
    1.53
     Kitchen
    1.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.