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. 13143
    Prev
    Next
    INDEX
    Explanations

    phrases related to high-quality construction and performance components

    oai_token-act-pair · gpt-3.5-turbo

    elements related to high performance and quality in products, particularly in automotive or technology contexts

    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
    angered
    -0.75
    ossip
    -0.73
     libel
    -0.73
     boycot
    -0.73
     Republican
    -0.73
    Topic
    -0.73
    Republican
    -0.71
     Rape
    -0.70
     newspapers
    -0.69
    Ask
    -0.68
    POSITIVE LOGITS
     util
    1.17
     utilizing
    1.09
     ensured
    1.09
     combining
    1.07
     utilizes
    1.06
     ingenious
    1.05
     seamlessly
    1.04
     incorporates
    1.02
     incorporating
    1.01
     ensures
    0.97
    Activations Density 0.824%

    No Known Activations