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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 19588
    Prev
    Next
    INDEX
    Explanations

    mentions of physical and mental fatigue

    oai_token-act-pair · gpt-3.5-turbo

    references to fatigue-related topics

    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
    ripp
    -0.78
     shady
    -0.75
     Moss
    -0.75
     Famous
    -0.75
    famous
    -0.74
    roc
    -0.73
    reme
    -0.73
     Lancaster
    -0.73
     Gors
    -0.71
    google
    -0.70
    POSITIVE LOGITS
     fatigue
    2.26
    atoon
    1.56
     fatig
    1.37
     exhaustion
    1.05
     brace
    1.00
     eurozone
    0.99
    asma
    0.98
     Guam
    0.95
     Payton
    0.95
     midterm
    0.93
    Activations Density 0.048%

    No Known Activations