Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15246
    Prev
    Next
    INDEX
    Explanations

    words related to gut health and microbial balance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gut health and beneficial bacteria

    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
    Tesla
    -0.95
    DCS
    -0.94
    Nik
    -0.92
    gpu
    -0.92
     Henderson
    -0.87
     Kidd
    -0.82
     Polaris
    -0.80
     Nissan
    -0.80
    dash
    -0.80
    iHUD
    -0.79
    POSITIVE LOGITS
     antibiotic
    2.06
     antibiotics
    1.91
     bacteria
    1.87
     bacterial
    1.86
     bacter
    1.84
     microbi
    1.78
     microbial
    1.76
     microbiome
    1.67
     microbes
    1.65
     microbiota
    1.62
    Activations Density 0.170%

    No Known Activations