© 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. 2-ATT-KK
    11. 21567
    Prev
    Next
    INDEX
    Explanations

    references to the character Mega Man and related elements from the franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.07
    2:0.20
    3:0.07
    4:0.13
    5:0.06
    6:0.03
    7:0.03
    8:0.05
    9:0.13
    10:0.05
    11:0.03
    Negative Logits
     omission
    -1.74
     malice
    -1.47
     principled
    -1.45
     maternity
    -1.42
     reconc
    -1.37
    displayText
    -1.33
     inspection
    -1.33
     appointed
    -1.31
     wounded
    -1.29
    pret
    -1.28
    POSITIVE LOGITS
    apon
    1.84
    ombat
    1.82
    Torrent
    1.69
    Pixel
    1.69
    Pokemon
    1.63
    rencies
    1.62
    atinum
    1.59
    Magikarp
    1.59
    Double
    1.56
    Extreme
    1.53
    Activations Density 0.003%

    No Known Activations