© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 22177
    Prev
    Next
    INDEX
    Explanations

    institutions or entities named "Johns Hopkins University" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to universities and academic institutions

    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
    bre
    -0.74
    ppings
    -0.69
    meaning
    -0.67
    lyak
    -0.65
    versions
    -0.63
    sticks
    -0.63
    ãĤ¯
    -0.62
    Bey
    -0.61
    Owner
    -0.61
     clauses
    -0.61
    POSITIVE LOGITS
     University
    0.98
     Libraries
    0.92
     Universities
    0.91
     undergrad
    0.91
     Research
    0.88
     undergraduate
    0.88
     Laboratory
    0.87
     laboratories
    0.87
     faculty
    0.85
     physicist
    0.85
    Activations Density 0.106%

    No Known Activations