© 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. 3-RES-JB
    6. 9728
    Prev
    Next
    INDEX
    Explanations

    phrases related to yeast

    oai_token-act-pair · gpt-3.5-turbo

    references to yeast and fermentation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lumpur
    -0.77
    oru
    -0.74
    vernment
    -0.72
    nels
    -0.71
    vertis
    -0.71
    ointed
    -0.71
    ciating
    -0.70
    awaru
    -0.68
    Guard
    -0.67
    undai
    -0.67
    POSITIVE LOGITS
     yeast
    1.10
     fermentation
    1.09
     ferment
    0.94
     fermented
    0.92
     nutrient
    0.91
     fungus
    0.91
     bacteria
    0.83
     infections
    0.83
    warm
    0.82
     cells
    0.81
    Activations Density 0.009%

    No Known Activations