© 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. 2230
    Prev
    Next
    INDEX
    Explanations

    keywords related to finance and industry

    oai_token-act-pair · gpt-3.5-turbo

    topics related to technology and its impact on health and society

    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
     senate
    -0.84
     chancellor
    -0.73
     republican
    -0.71
     dart
    -0.70
     knight
    -0.69
     aven
    -0.68
     queen
    -0.68
     corps
    -0.68
     dwarves
    -0.67
     knights
    -0.67
    POSITIVE LOGITS
     Needs
    1.39
     Names
    1.39
     Practices
    1.36
     Problems
    1.35
     Functions
    1.33
     Practice
    1.32
     Advice
    1.31
     Uses
    1.31
     Costs
    1.31
     Coverage
    1.31
    Activations Density 1.089%

    No Known Activations