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. 10-RES-JB
    6. 9543
    Prev
    Next
    INDEX
    Explanations

    references to different types of technologies and industries, including renewable energy, security apparatus, social media, and biotech companies

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to energy, environmental sustainability, and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eday
    -0.66
    ethe
    -0.65
    omever
    -0.65
    ï¸
    -0.65
    é¾įåĸļ士
    -0.65
    ulu
    -0.63
    None
    -0.63
    ãĥ´ãĤ¡
    -0.63
    acly
    -0.62
    ciating
    -0.62
    POSITIVE LOGITS
     calculator
    0.75
     mural
    0.71
     scams
    0.68
     syndrome
    0.67
     thriller
    0.66
     vehicle
    0.66
     planner
    0.65
     technician
    0.65
     kit
    0.65
     strategy
    0.64
    Activations Density 0.562%

    No Known Activations