© 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. 16143
    Prev
    Next
    INDEX
    Explanations

    financial and personal identification information

    oai_token-act-pair · gpt-3.5-turbo

    references to customer data and personal information in a privacy or security context

    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
     Racer
    -0.76
    starter
    -0.75
    uve
    -0.72
    nesty
    -0.72
    rossover
    -0.72
    nesday
    -0.70
     Huckabee
    -0.69
    assador
    -0.69
    iege
    -0.69
    moderate
    -0.68
    POSITIVE LOGITS
     records
    1.44
     histories
    1.43
     transcripts
    1.43
     data
    1.42
     documents
    1.39
     information
    1.39
     databases
    1.33
     files
    1.31
     datasets
    1.28
     logs
    1.28
    Activations Density 0.383%

    No Known Activations