© 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. 10-RES-JB
    11. 4980
    Prev
    Next
    INDEX
    Explanations

    references to medical treatments and conditions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and other special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Full stop at the end of sentences about conspiracies.

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     challeng
    -0.77
     wre
    -0.75
    ensibly
    -0.72
     advoc
    -0.71
    iliated
    -0.70
     painfully
    -0.69
     exclusively
    -0.69
     predec
    -0.68
     accumulated
    -0.68
    anting
    -0.68
    POSITIVE LOGITS
     Anyway
    1.15
     Logged
    1.06
     Reply
    1.06
     UNCLASSIFIED
    1.06
     ********************************
    1.05
     Lastly
    1.05
     ----------------------------------------------------------------
    1.04
     Otherwise
    1.03
     Conclusion
    1.03
     Others
    1.02
    Activations Density 0.737%

    No Known Activations