© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14937
    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
    2:0.07
    3:0.08
    4:0.08
    5:0.07
    6:0.09
    7:0.07
    8:0.09
    9:0.10
    10:0.08
    11:0.08
    Negative Logits
     Gujar
    -3.44
     ―
    -2.96
     tenancy
    -2.95
    \\\\\\\\
    -2.85
     renters
    -2.74
     Louisiana
    -2.63
     eviction
    -2.58
     authenticity
    -2.58
     Maharashtra
    -2.58
     affordability
    -2.52
    POSITIVE LOGITS
    zza
    3.07
    scroll
    2.85
     Round
    2.83
     Tuc
    2.80
    Stretch
    2.74
     Stretch
    2.70
    uchin
    2.70
    usky
    2.68
    aug
    2.64
    uca
    2.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.