© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 17413
    Prev
    Next
    INDEX
    Explanations

    medical procedures or processes related to wounds, cells, and electrode seeding

    oai_token-act-pair · gpt-3.5-turbo

    references to medical or scientific processes and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Conclusion
    -0.75
     :(
    -0.75
     Conclusion
    -0.75
    ''.
    -0.71
    CONCLUS
    -0.70
     Yesterday
    -0.68
    ?".
    -0.68
    }.
    -0.66
     Verse
    -0.64
    Advertisements
    -0.63
    POSITIVE LOGITS
     anonymously
    1.02
     periodically
    1.01
    fitted
    0.98
     randomly
    0.91
     whenever
    0.86
     via
    0.86
     wherever
    0.85
     electronically
    0.84
     ranging
    0.84
     individually
    0.84
    Activations Density 0.565%

    No Known Activations