© 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. 21308
    Prev
    Next
    INDEX
    Explanations

    references to the character Spider-Man and associated comic book narratives

    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
    0:0.33
    1:0.04
    2:0.04
    3:0.03
    4:0.05
    5:0.02
    6:0.04
    7:0.12
    8:0.01
    9:0.06
    10:0.15
    11:0.04
    Negative Logits
     Eston
    -3.52
    �
    -3.40
    hw
    -3.38
     Punjab
    -3.31
     Estonia
    -3.31
     Baltic
    -3.29
     Kelley
    -3.29
     Yemeni
    -3.25
     Yemen
    -3.23
     RBI
    -3.20
    POSITIVE LOGITS
    Spider
    8.40
     Spider
    8.35
     Venom
    6.59
     spider
    5.69
     Parker
    5.20
    Marvel
    5.07
     spiders
    4.80
     Marvel
    4.72
     Osc
    4.70
     superhero
    4.52
    Activations Density 0.047%

    No Known Activations