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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 9336
    Prev
    Next
    INDEX
    Explanations

    references to scientific journals and their associated metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    0:0.15
    1:0.08
    2:0.03
    3:0.06
    4:0.05
    5:0.06
    6:0.10
    7:0.07
    8:0.03
    9:0.05
    10:0.23
    11:0.05
    Negative Logits
     Hind
    -3.56
     marqu
    -3.21
     XY
    -2.91
     duct
    -2.86
     WM
    -2.78
    Mc
    -2.78
     HK
    -2.71
     Wolver
    -2.70
     McDonald
    -2.70
     furnace
    -2.69
    POSITIVE LOGITS
     PLoS
    4.69
    oS
    3.65
    peer
    3.58
     Peer
    3.30
    opus
    3.17
     Io
    3.14
    Phys
    3.08
    nih
    3.02
     Sagan
    3.00
    Ven
    2.96
    Activations Density 0.001%

    No Known Activations