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. 6-RES-JB
    6. 15910
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical substances and treatments, such as herbs and pharmaceuticals

    oai_token-act-pair · gpt-3.5-turbo

    references to various substances and technologies related to health and finance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Frey
    -0.64
     Syd
    -0.64
    æĪ¦
    -0.63
    Thom
    -0.63
    ¦
    -0.63
     Browne
    -0.62
     Gaia
    -0.61
     Thom
    -0.60
    olulu
    -0.60
     Byron
    -0.60
    POSITIVE LOGITS
     proponents
    0.79
     behaves
    0.78
     facilitates
    0.78
     exists
    0.77
     substitutes
    0.74
     advocates
    0.74
     signifies
    0.74
     produces
    0.72
     eliminates
    0.71
     shines
    0.71
    Activations Density 0.405%

    No Known Activations