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. 11-RES-JB
    6. 8293
    Prev
    Next
    INDEX
    Explanations

    mentions of children

    oai_token-act-pair · gpt-3.5-turbo

    references to children or kids in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Centauri
    -0.77
     manifold
    -0.70
    phas
    -0.69
    uncture
    -0.67
    obook
    -0.67
    omination
    -0.64
     freight
    -0.63
    gments
    -0.63
    Client
    -0.62
    gment
    -0.62
    POSITIVE LOGITS
    kids
    0.97
     ages
    0.95
    ults
    0.90
     kindergarten
    0.86
     kids
    0.85
    chool
    0.85
     puberty
    0.83
    kid
    0.83
    girl
    0.80
     leukemia
    0.78
    Activations Density 0.041%

    No Known Activations