© 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. 0-RES-JB
    11. 18335
    Prev
    Next
    INDEX
    Explanations

    mineral and nutrient information, particularly about sodium and potassium levels

    oai_token-act-pair · gpt-3.5-turbo

    nutritional components and elements related to sodium and potassium

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Huss
    -0.86
    Laun
    -0.83
     Hug
    -0.75
     Wolves
    -0.74
     Marco
    -0.74
     Riders
    -0.74
     Observer
    -0.74
     Rapt
    -0.73
     Crus
    -0.72
    Commerce
    -0.71
    POSITIVE LOGITS
     potassium
    2.99
     sodium
    2.97
     calcium
    2.46
     magnesium
    2.33
     vitamin
    2.21
     Sodium
    2.04
     Vitamin
    2.01
     zinc
    1.94
     phosphorus
    1.88
     methyl
    1.85
    Activations Density 0.038%

    No Known Activations