Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 7128
    Prev
    Next
    INDEX
    Explanations

    key terms related to medical procedures, biological functions, and materials used in healthcare and biotechnology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to biological and medical materials, processes, and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nces
    -0.92
    ilitary
    -0.87
    xual
    -0.86
    女
    -0.80
    ļéĨĴ
    -0.76
    iquette
    -0.71
    Ire
    -0.70
     Rowe
    -0.69
    å§«
    -0.69
     blat
    -0.68
    POSITIVE LOGITS
     proteins
    0.76
    âĢIJ
    0.75
     phenotype
    0.72
    ,[
    0.72
     nucle
    0.72
     nucleus
    0.71
    like
    0.67
     ®
    0.67
     DNA
    0.67
     rad
    0.67
    Activations Density 0.490%

    No Known Activations