© 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 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. 7-RES-JB
    11. 20774
    Prev
    Next
    INDEX
    Explanations

    terms related to news articles or journalistic content

    oai_token-act-pair · gpt-3.5-turbo

    special markers or indicators that signal the end of a segment or a distinct separation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atever
    -0.69
    gling
    -0.67
    iterranean
    -0.62
    bley
    -0.61
    xtap
    -0.59
     Pric
    -0.59
     Sons
    -0.59
    rowing
    -0.57
    $.
    -0.57
    Ms
    -0.56
    POSITIVE LOGITS
     âĢº
    0.76
     >>
    0.69
     ][
    0.68
    ==
    0.68
    ---------
    0.68
     0004
    0.68
     partName
    0.67
    actionDate
    0.65
     ARTICLE
    0.64
     summary
    0.64
    Activations Density 0.207%

    No Known Activations