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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 12950
    Prev
    Next
    INDEX
    Explanations

    proper nouns from the Mortal Kombat universe

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "MK" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥ³
    -0.82
     Reaper
    -0.79
    aceous
    -0.77
    cean
    -0.72
    ================================================================
    -0.71
     Hurricanes
    -0.71
    Interstitial
    -0.68
    ãĥ¼ãĥĨ
    -0.68
    ãĥ³ãĤ¸
    -0.66
     Governments
    -0.66
    POSITIVE LOGITS
    MK
    1.04
     MK
    1.02
    JV
    0.80
    Ultra
    0.80
    adish
    0.77
    FY
    0.75
    enzie
    0.74
    ernel
    0.73
    ULT
    0.72
    TG
    0.71
    Activations Density 0.009%

    No Known Activations