© 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. 8327
    Prev
    Next
    INDEX
    Explanations

    references to individuals or concepts that evoke concern or risk

    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
    0:0.02
    1:0.01
    2:0.03
    3:0.02
    4:0.05
    5:0.62
    6:0.02
    7:0.02
    8:0.02
    9:0.08
    10:0.02
    11:0.03
    Negative Logits
     refuses
    -3.45
     accuses
    -3.45
     warns
    -3.44
     lately
    -3.31
     publishes
    -3.27
     Says
    -3.26
     continues
    -3.19
     Adds
    -3.12
     complains
    -3.10
     Provides
    -3.00
    POSITIVE LOGITS
    would
    6.81
     would
    6.65
     wouldn
    5.77
    Would
    5.61
     Would
    5.50
     mattered
    5.41
    'd
    5.37
     depended
    5.18
    Had
    5.05
     belonged
    4.91
    Activations Density 1.587%

    No Known Activations