© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 14544
    Prev
    Next
    INDEX
    Explanations

    terms related to specific dietary components, specifically sodium

    oai_token-act-pair · gpt-3.5-turbo

    references to sodium and aluminum content in food or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atted
    -0.83
    leaders
    -0.79
    furt
    -0.78
    eme
    -0.78
    imaru
    -0.77
    ete
    -0.76
    er
    -0.75
    etary
    -0.75
    eting
    -0.75
     Generations
    -0.74
    POSITIVE LOGITS
     foil
    0.86
    ä¿
    0.76
     neurot
    0.73
     glutamate
    0.71
    ELF
    0.70
    ç«
    0.69
     chloride
    0.68
    gency
    0.68
    kson
    0.68
     Lumpur
    0.67
    Activations Density 0.077%

    No Known Activations