© 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. 10-RES-JB
    11. 11601
    Prev
    Next
    INDEX
    Explanations

    references to the "Final Fantasy" video game series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    keywords related to the video game series "Final Fantasy."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holes
    -0.76
     urgently
    -0.64
     Huck
    -0.63
     ministries
    -0.62
     abundantly
    -0.61
     incess
    -0.60
     simultaneously
    -0.60
    gypt
    -0.60
    shire
    -0.59
    zee
    -0.58
    POSITIVE LOGITS
    izers
    1.16
    izing
    1.07
     FANTASY
    1.01
     Destination
    1.00
    ists
    0.99
    ize
    0.99
     Fantasy
    0.98
    ised
    0.96
    izer
    0.96
    isers
    0.96
    Activations Density 0.034%

    No Known Activations