© 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. 1090
    Prev
    Next
    INDEX
    Explanations

    sequences containing technical instructions or chemical processes

    oai_token-act-pair · gpt-3.5-turbo

    references to current status or actions

    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
     POLITICO
    -0.74
     grassroots
    -0.74
     swath
    -0.66
     millennials
    -0.66
     paycheck
    -0.63
     vetted
    -0.63
     âĢķ
    -0.63
     LGBTQ
    -0.62
     Marketplace
    -0.62
     uptick
    -0.62
    POSITIVE LOGITS
     Conclusion
    0.88
    CONCLUS
    0.84
     embodiments
    0.83
     diagrams
    0.77
     Canaver
    0.75
     FIG
    0.74
     Specifications
    0.74
     Experiment
    0.72
     diagram
    0.72
     accur
    0.71
    Activations Density 1.047%

    No Known Activations