Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 9334
    Prev
    Next
    INDEX
    Explanations

    the term "MP3" or variations of it (like MP3s or MP3 player)

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of media formats and file extensions

    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
    abouts
    -0.70
    mare
    -0.66
    inav
    -0.66
    infeld
    -0.65
    wcs
    -0.65
    ussie
    -0.65
     Schwarz
    -0.64
     Franch
    -0.64
    afety
    -0.64
    hani
    -0.62
    POSITIVE LOGITS
     IMAGES
    0.97
    archive
    0.93
    IFF
    0.89
    Artist
    0.88
     Mehran
    0.83
    Upload
    0.81
    uploads
    0.80
    TAG
    0.79
    DragonMagazine
    0.78
    URL
    0.78
    Activations Density 0.118%

    No Known Activations