© 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. 8-RES-JB
    11. 4279
    Prev
    Next
    INDEX
    Explanations

    special characters and code-related terms

    oai_token-act-pair · gpt-3.5-turbo

    fragments of code and programming terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cherished
    -0.76
     girls
    -0.76
     foul
    -0.76
     furthe
    -0.72
     Mayor
    -0.72
     Hancock
    -0.72
     estranged
    -0.71
     photographed
    -0.71
     hers
    -0.71
     Nath
    -0.71
    POSITIVE LOGITS
    Example
    1.61
    Usage
    1.58
    Installation
    1.48
    Examples
    1.42
    Parameters
    1.41
    Setup
    1.41
    Using
    1.39
    HTTP
    1.36
    Methods
    1.34
    Install
    1.33
    Activations Density 0.277%

    No Known Activations