© 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. 1-RES-JB
    11. 3872
    Prev
    Next
    INDEX
    Explanations

    mentions of specific books

    oai_token-act-pair · gpt-3.5-turbo

    references to various books, particularly the "Book of Mormon."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.81
    ilitary
    -0.77
    asio
    -0.72
    00200000
    -0.69
    udge
    -0.65
    isin
    -0.64
     sclerosis
    -0.63
    hap
    -0.63
     cease
    -0.62
     permanent
    -0.61
    POSITIVE LOGITS
    stores
    1.23
    book
    1.23
     Book
    1.18
    Book
    1.16
    marks
    1.07
    worm
    1.01
    books
    0.98
    mark
    0.98
    worms
    0.94
    seller
    0.94
    Activations Density 0.012%

    No Known Activations