© 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. 2-RES-JB
    11. 17506
    Prev
    Next
    INDEX
    Explanations

    table of contents sections in a document

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of content or table of contents markers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eg
    -0.90
    ee
    -0.79
    umble
    -0.77
    rive
    -0.74
    pled
    -0.71
    roud
    -0.70
     bliss
    -0.70
    orney
    -0.68
    VP
    -0.66
    unning
    -0.65
    POSITIVE LOGITS
    Contents
    1.25
    éļ
    0.82
    tenance
    0.78
     lett
    0.77
     Contents
    0.76
    ä¹ĭ
    0.75
    enhagen
    0.74
    chwitz
    0.74
    [[
    0.72
    Thumbnail
    0.71
    Activations Density 0.011%

    No Known Activations