© 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. 1261
    Prev
    Next
    INDEX
    Explanations

    titles or headings within a technical domain

    oai_token-act-pair · gpt-3.5-turbo

    instances of special characters or punctuation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     ranged
    -0.97
     administr
    -0.95
     qualified
    -0.91
     pse
    -0.88
     favour
    -0.87
     manifest
    -0.87
     range
    -0.86
     neut
    -0.85
     foreseeable
    -0.84
     cons
    -0.84
    POSITIVE LOGITS
    Advertisements
    1.54
    Cele
    1.45
    Interview
    1.45
    Conclusion
    1.44
    Meet
    1.43
    Review
    1.42
    Latest
    1.40
    Introdu
    1.40
    Inside
    1.40
    Learn
    1.39
    Activations Density 0.240%

    No Known Activations