© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 17361
    Prev
    Next
    INDEX
    Explanations

    elements related to "Mortal Kombat" video game series

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Mortal Kombat" franchise and its characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ously
    -0.86
    etts
    -0.79
    cies
    -0.77
    olf
    -0.76
    Interstitial
    -0.75
    esses
    -0.73
    wall
    -0.72
    istics
    -0.72
    acea
    -0.68
    uation
    -0.67
    POSITIVE LOGITS
    Ultra
    0.84
    iltr
    0.70
    MK
    0.68
    heat
    0.67
    othal
    0.66
     disadvant
    0.66
    ellectual
    0.64
    ellen
    0.62
    cel
    0.62
    rity
    0.62
    Activations Density 0.036%

    No Known Activations