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

    Neuronpedia

    APICircuit 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. 16318
    Prev
    Next
    INDEX
    Explanations

    keywords related to electronic reading devices, especially the Kindle

    oai_token-act-pair · gpt-3.5-turbo

    references to the Kindle and its associated versions or formats

    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
    nel
    -0.85
    apolis
    -0.71
    amen
    -0.70
    xon
    -0.69
    amera
    -0.69
     Lumpur
    -0.68
    dinand
    -0.68
    ndum
    -0.67
     rigs
    -0.66
    ocre
    -0.65
    POSITIVE LOGITS
    Books
    1.14
     Journals
    1.11
    lishing
    1.05
     books
    0.98
     ebook
    0.92
     manuscript
    0.92
     manuscripts
    0.89
     Fiction
    0.87
    books
    0.87
     Books
    0.86
    Activations Density 0.108%

    No Known Activations