© 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. 22426
    Prev
    Next
    INDEX
    Explanations

    elements related to lighting and illumination in various contexts

    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
    0:0.20
    1:0.12
    2:0.07
    3:0.06
    4:0.07
    5:0.02
    6:0.05
    7:0.09
    8:0.02
    9:0.05
    10:0.08
    11:0.13
    Negative Logits
     Strauss
    -3.32
     Slaughter
    -3.11
    Sullivan
    -3.07
     Sullivan
    -3.00
     Gork
    -2.83
     Wolves
    -2.79
     Spiel
    -2.79
     Moose
    -2.78
     Savage
    -2.77
     Palin
    -2.77
    POSITIVE LOGITS
     LED
    7.21
     LEDs
    7.10
     lighting
    7.05
     lamps
    6.60
     Lighting
    6.38
    LED
    6.36
     lights
    5.72
     bulbs
    5.71
     illumination
    5.71
     lamp
    5.46
    Activations Density 0.098%

    No Known Activations