© 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. 8-RES-JB
    11. 18659
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the term "Final Fantasy" within text

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Final Fantasy" video game series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holes
    -0.74
     ministries
    -0.72
    gypt
    -0.71
    lein
    -0.64
    growth
    -0.62
    shire
    -0.62
     charism
    -0.62
    kun
    -0.61
    lez
    -0.60
    MAN
    -0.59
    POSITIVE LOGITS
    izers
    1.07
     FANTASY
    1.06
    izing
    1.02
    ization
    0.96
     Fantasy
    0.96
    ised
    0.96
    ists
    0.96
    izes
    0.95
    izer
    0.91
    ize
    0.91
    Activations Density 0.033%

    No Known Activations