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. 1-RES-JB
    6. 1307
    Prev
    Next
    INDEX
    Explanations

    words related to health and healthy living

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being healthy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atography
    -0.67
     angrily
    -0.66
     infamous
    -0.66
     borrowed
    -0.66
    personal
    -0.65
    inatory
    -0.64
    clip
    -0.64
     towed
    -0.64
     swoop
    -0.64
    Blade
    -0.63
    POSITIVE LOGITS
    iterranean
    0.94
     healthy
    0.92
    tarian
    0.84
    healthy
    0.80
     healthier
    0.80
     eater
    0.78
     isot
    0.75
     nutritious
    0.70
    ":[
    0.69
    Health
    0.68
    Activations Density 0.008%

    No Known Activations