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. 3911
    Prev
    Next
    INDEX
    Explanations

    mentions or discussions of diversity

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of diversity

    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
     Pry
    -0.82
    akin
    -0.74
    «
    -0.73
    fax
    -0.71
    aper
    -0.71
    oto
    -0.69
    ivan
    -0.68
     Cancel
    -0.67
    teen
    -0.66
    AH
    -0.66
    POSITIVE LOGITS
     diversity
    3.77
     Diversity
    2.82
    iversity
    2.04
     diverse
    1.87
     heterogeneity
    1.78
     richness
    1.78
     biodiversity
    1.68
     multicultural
    1.68
    clus
    1.59
     minorities
    1.56
    Activations Density 0.014%

    No Known Activations