Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 16588
    Prev
    Next
    INDEX
    Explanations

    terms related to computer programming, specifically focusing on SQL, JSON, XML, and PowerShell

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and concepts related to computing or software development

    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
     Vaugh
    -0.62
    fur
    -0.62
     Vaughan
    -0.56
     Mub
    -0.56
    deen
    -0.54
     convictions
    -0.54
     Tanz
    -0.51
     Socialist
    -0.50
     socialism
    -0.50
     sovere
    -0.50
    POSITIVE LOGITS
     translucent
    0.63
     approximate
    0.61
     DATA
    0.60
    ITNESS
    0.60
     LIMITED
    0.59
     DEBUG
    0.59
     UDP
    0.55
     user
    0.54
     User
    0.54
     TYPE
    0.54
    Activations Density 4.503%

    No Known Activations