© 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. 9539
    Prev
    Next
    INDEX
    Explanations

    prominent movie references and mentions of cinematic features

    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
    0:0.28
    1:0.05
    2:0.06
    3:0.07
    4:0.05
    5:0.02
    6:0.05
    7:0.12
    8:0.02
    9:0.05
    10:0.13
    11:0.05
    Negative Logits
    henko
    -4.40
     Braves
    -3.58
     Sounders
    -3.57
     Sakuya
    -3.55
     Kiev
    -3.52
    Balt
    -3.32
     Belarus
    -3.31
     Uk
    -3.21
    о
    -3.21
    hw
    -3.18
    POSITIVE LOGITS
     Jurassic
    8.52
    assic
    6.41
     dinosaurs
    5.87
     Dinosaur
    5.56
     dinosaur
    5.48
     Tyrann
    4.62
     Spielberg
    3.88
    inosaur
    3.73
     prehistoric
    3.73
    osaurs
    3.71
    Activations Density 0.002%

    No Known Activations