© 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. 9-RES-JB
    11. 15604
    Prev
    Next
    INDEX
    Explanations

    phrases related to user agreement and instructions

    oai_token-act-pair · gpt-3.5-turbo

    the end of text markers or indicate the conclusion of content sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?ãĢį
    -0.70
     damned
    -0.68
    .","
    -0.66
    ––
    -0.64
    .ãĢį
    -0.63
     ''
    -0.61
     mush
    -0.60
    .</
    -0.59
     insofar
    -0.59
    toggle
    -0.59
    POSITIVE LOGITS
    resa
    1.04
    odore
    1.03
    notations
    0.99
    ibliography
    0.99
     Contents
    0.93
     Conclusion
    0.92
    mosp
    0.91
    iple
    0.90
    bidden
    0.89
    chieve
    0.89
    Activations Density 0.397%

    No Known Activations