© 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. 0-RES-JB
    6. 8199
    Prev
    Next
    INDEX
    Explanations

    keywords related to the concept of "gut", including different contexts like emotions, physical actions, and politics

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "gut" and its variations

    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
     Cooperation
    -0.71
    ature
    -0.71
     Contest
    -0.69
    xxx
    -0.67
    iri
    -0.66
     Matters
    -0.66
     00
    -0.65
    ords
    -0.64
     Caldwell
    -0.64
    X
    -0.64
    POSITIVE LOGITS
     gut
    3.96
     Gut
    2.07
     guts
    1.94
     intestinal
    1.46
     stomach
    1.42
     microbiome
    1.38
     visceral
    1.32
     microbiota
    1.22
     intest
    1.20
    estinal
    1.15
    Activations Density 0.013%

    No Known Activations