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. 10001
    Prev
    Next
    INDEX
    Explanations

    keywords or terms related to summarizing or reviewing content, often in a structured manner

    oai_token-act-pair · gpt-3.5-turbo

    references to recaps or summaries of events or content

    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
    train
    -0.76
     Breed
    -0.66
     Mustang
    -0.63
     Wee
    -0.63
    Age
    -0.63
     Laboratory
    -0.59
    erness
    -0.57
     marriage
    -0.57
    Fish
    -0.56
     Marriage
    -0.56
    POSITIVE LOGITS
    ital
    1.24
     recap
    1.05
    ocial
    0.89
    ilitation
    0.88
    itations
    0.87
    undown
    0.86
    itual
    0.86
    alon
    0.86
    rast
    0.86
    spective
    0.85
    Activations Density 0.013%

    No Known Activations