© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-ATT-KK
    11. 21104
    Prev
    Next
    INDEX
    Explanations

    references to iconic characters associated with Thor in mythology and the Marvel universe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.01
    2:0.08
    3:0.06
    4:0.02
    5:0.07
    6:0.07
    7:0.05
    8:0.38
    9:0.05
    10:0.02
    11:0.03
    Negative Logits
     PSP
    -3.98
     Nicarag
    -3.68
    Ohio
    -3.68
     Dominican
    -3.62
     Maduro
    -3.60
     Akron
    -3.54
     Petraeus
    -3.39
     CPC
    -3.33
     pes
    -3.27
     Cincinnati
    -3.27
    POSITIVE LOGITS
     Asgard
    9.09
     Thor
    7.98
    Thor
    7.83
     Loki
    7.42
     Ragnarok
    7.24
     Norse
    7.20
     Odin
    7.14
     Ragnar
    6.92
    agnar
    5.72
     Viking
    5.55
    Activations Density 0.018%

    No Known Activations