© 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. 19409
    Prev
    Next
    INDEX
    Explanations

    references to numerical comparisons and statistics

    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
    0:0.03
    1:0.03
    2:0.03
    3:0.04
    4:0.04
    5:0.03
    6:0.04
    7:0.05
    8:0.02
    9:0.14
    10:0.03
    11:0.48
    Negative Logits
     Canaver
    -2.29
     Editorial
    -2.09
     Stephan
    -2.00
    guide
    -2.00
    guided
    -1.94
     Partners
    -1.92
     Expand
    -1.90
    odon
    -1.87
     Experiment
    -1.86
     Wonderland
    -1.85
    POSITIVE LOGITS
     rates
    4.42
     levels
    4.13
     incomes
    3.64
     Rates
    3.63
     numbers
    3.57
    levels
    3.49
     percentages
    3.46
     temperatures
    3.42
     prices
    3.34
     scores
    3.32
    Activations Density 0.332%

    No Known Activations