© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 340
    Prev
    Next
    INDEX
    Explanations

    references to PDF files

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "PDF" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acha
    -0.77
    inence
    -0.77
    hma
    -0.75
    places
    -0.75
    allow
    -0.73
    esthetic
    -0.70
    inent
    -0.69
    asts
    -0.68
    dinand
    -0.68
    venge
    -0.68
    POSITIVE LOGITS
    PDF
    1.31
    pdf
    1.09
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.95
    DragonMagazine
    0.94
     PDF
    0.87
     pdf
    0.86
    pedia
    0.78
    archive
    0.76
    TeX
    0.76
     transcript
    0.71
    Activations Density 0.006%

    No Known Activations