© 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. 10-RES-JB
    11. 13971
    Prev
    Next
    INDEX
    Explanations

    terms related to Bayesian statistics and mathematical modeling

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical and mathematical modeling techniques in data analysis

    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
    ][/
    -0.80
    uggage
    -0.74
    advertising
    -0.73
    etsy
    -0.73
    arag
    -0.70
     Amend
    -0.69
    artisan
    -0.69
     Lobby
    -0.69
     Spirits
    -0.69
    kiss
    -0.69
    POSITIVE LOGITS
     algorithms
    1.74
     algorithm
    1.65
     computational
    1.64
     simulations
    1.56
     algorith
    1.56
     dataset
    1.50
     comput
    1.50
     mathematical
    1.44
     datasets
    1.43
     theorem
    1.42
    Activations Density 0.537%

    No Known Activations