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. 4-RES-JB
    6. 5839
    Prev
    Next
    INDEX
    Explanations

    mentions of a variety of things or topics in a document

    oai_token-act-pair · gpt-3.5-turbo

    mentions of 'various' to indicate diversity or multiple aspects

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

    No Comments

    Negative Logits
    ocene
    -0.73
    vest
    -0.72
    O
    -0.70
    abad
    -0.69
    itten
    -0.67
    cher
    -0.65
     thence
    -0.64
    athing
    -0.64
    uberty
    -0.63
    $$$$
    -0.63
    POSITIVE LOGITS
    iating
    1.29
     kinds
    1.28
     sorts
    1.12
     aspects
    1.06
     iterations
    1.03
     facets
    1.02
     types
    1.01
     parts
    0.96
    iated
    0.95
     degrees
    0.94
    Activations Density 0.021%

    No Known Activations