© 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 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. 42413
    Prev
    Next
    INDEX
    Explanations

    terms related to graphic design and rendering processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    0:0.05
    1:0.02
    2:0.05
    3:0.05
    4:0.04
    5:0.05
    6:0.06
    7:0.05
    8:0.06
    9:0.05
    10:0.13
    11:0.35
    Negative Logits
     painter
    -1.81
     Painting
    -1.79
     Thumbnails
    -1.77
     Sketch
    -1.76
     Graphic
    -1.76
     paintings
    -1.75
    ThumbnailImage
    -1.75
     masterpiece
    -1.74
     painting
    -1.73
     portraits
    -1.70
    POSITIVE LOGITS
     deposit
    1.70
     finance
    1.63
     prescribing
    1.55
     guarantee
    1.55
     withdrawal
    1.55
     reimburse
    1.51
     fund
    1.49
    ertodd
    1.49
    cium
    1.48
     subsid
    1.47
    Activations Density 0.242%

    No Known Activations