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. 22794
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms related to biological processes and research

    oai_token-act-pair · gpt-3.5-turbo

    sentences or segments that contain medical or scientific facts

    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
     vigilante
    -0.87
     grievance
    -0.86
     condos
    -0.83
     hourly
    -0.79
     estate
    -0.78
     enforcement
    -0.78
     plead
    -0.77
     discretionary
    -0.77
     franch
    -0.77
     enforce
    -0.77
    POSITIVE LOGITS
    Researchers
    1.64
     Researchers
    1.51
    Scientists
    1.51
    Explore
    1.41
    Previous
    1.34
     Scientists
    1.32
    Professor
    1.28
    Study
    1.26
    Abstract
    1.20
    Using
    1.18
    Activations Density 0.269%

    No Known Activations