© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 994
    Prev
    Next
    INDEX
    Explanations

    content-related terms often found in a structured document, such as "Contents", "Edit", "Trivia," and "RAW."

    oai_token-act-pair · gpt-3.5-turbo

    structured data and references in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eg
    -0.81
    ee
    -0.77
    uez
    -0.70
    rams
    -0.70
    oÄŁ
    -0.67
    ez
    -0.67
    iants
    -0.65
    ulously
    -0.64
    jee
    -0.64
    eco
    -0.63
    POSITIVE LOGITS
    tenance
    0.94
    Contents
    0.90
    ĸļ
    0.83
     "$:/
    0.76
    rawdownloadcloneembedreportprint
    0.71
    %]
    0.70
    ...]
    0.69
     Contents
    0.69
    pmwiki
    0.68
     marrow
    0.68
    Activations Density 0.028%

    No Known Activations