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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 9428
    Prev
    Next
    INDEX
    Explanations

    topics related to various sectors and industries, potentially news articles or information

    oai_token-act-pair · gpt-3.5-turbo

    key themes or topics related to various sectors, including development, food, politics, and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     center
    -0.73
     opposite
    -0.69
     core
    -0.67
     cycle
    -0.66
     centre
    -0.65
     tiny
    -0.63
     direction
    -0.63
     dime
    -0.62
     lit
    -0.62
     grace
    -0.62
    POSITIVE LOGITS
    tenance
    0.93
    cyclopedia
    0.93
    Doc
    0.91
    Tag
    0.91
    Analysis
    0.89
    Berry
    0.88
    Plot
    0.88
    Info
    0.87
    Folder
    0.86
    bnb
    0.85
    Activations Density 0.246%

    No Known Activations