© 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. 9-RES-JB
    6. 22879
    Prev
    Next
    INDEX
    Explanations

    ingredients and quantities in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    ingredients and measurements in recipes

    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
     trump
    -0.87
     glac
    -0.84
     curly
    -0.81
     increasingly
    -0.81
     widely
    -0.80
     flowing
    -0.79
     hotly
    -0.79
     previously
    -0.77
     prolifer
    -0.76
     habit
    -0.76
    POSITIVE LOGITS
    Conclusion
    1.89
    Advertisements
    1.74
    References
    1.60
    Notes
    1.55
    Other
    1.53
    Disclaimer
    1.50
    Translation
    1.50
    Total
    1.50
    Discussion
    1.49
    Others
    1.49
    Activations Density 0.174%

    No Known Activations