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. 8-RES-JB
    6. 20742
    Prev
    Next
    INDEX
    Explanations

    word stems related to the act of spreading or sharing information

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thro
    -0.75
    rap
    -0.72
    ney
    -0.72
    xa
    -0.71
    hetical
    -0.69
    rians
    -0.68
    iane
    -0.66
    inez
    -0.65
    este
    -0.65
    ree
    -0.64
    POSITIVE LOGITS
     circulate
    0.95
     freely
    0.89
    pmwiki
    0.89
     circulated
    0.85
     circulating
    0.76
    ickr
    0.75
     amongst
    0.72
    acebook
    0.72
     anonymously
    0.70
     circulation
    0.70
    Activations Density 0.055%

    No Known Activations