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

    Neuronpedia

    Jacobian LensNEW
    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. 16705
    Prev
    Next
    INDEX
    Explanations

    keywords related to software development and technology projects

    oai_token-act-pair · gpt-3.5-turbo

    references to core themes or elements concerning a project or topic

    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
    ansas
    -0.90
    SPONSORED
    -0.76
    agogue
    -0.75
    England
    -0.74
    Scotland
    -0.74
    antes
    -0.73
    atchewan
    -0.72
    Britain
    -0.70
    Lago
    -0.68
    ARDIS
    -0.67
    POSITIVE LOGITS
     simplest
    1.21
     backend
    1.18
     implementation
    1.17
     SDK
    1.15
     functionality
    1.14
     API
    1.12
     basics
    1.09
     core
    1.09
     GUI
    1.09
     workflow
    1.08
    Activations Density 0.341%

    No Known Activations