© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 28831
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    1:0.05
    2:0.09
    3:0.05
    4:0.08
    5:0.09
    6:0.07
    7:0.09
    8:0.09
    9:0.08
    10:0.09
    11:0.08
    Negative Logits
     HH
    -2.14
    hov
    -1.92
    endor
    -1.72
    AV
    -1.55
     Doomsday
    -1.54
     PP
    -1.53
     Modified
    -1.50
    ゼウス
    -1.49
     Apocalypse
    -1.48
    IDES
    -1.47
    POSITIVE LOGITS
    byn
    1.79
    journal
    1.71
    wcs
    1.68
    gow
    1.60
    tackle
    1.59
    spring
    1.54
    wage
    1.54
     mounting
    1.52
    ktop
    1.50
    pez
    1.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.