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. 6-RES-JB
    6. 23950
    Prev
    Next
    INDEX
    Explanations

    terms related to software development, specifically focusing on different aspects like profiles, tasks, shapes, applications, and registers

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to software and applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.64
    othe
    -0.63
    judicial
    -0.62
    oshop
    -0.62
    cffffcc
    -0.61
     British
    -0.61
    igl
    -0.60
    phia
    -0.59
     mornings
    -0.59
     Saturdays
    -0.58
    POSITIVE LOGITS
     identifier
    0.81
     initialization
    0.79
    \'
    0.75
     descriptor
    0.75
     configuration
    0.75
     \(
    0.74
    Id
    0.71
     pointer
    0.70
     instance
    0.70
     node
    0.69
    Activations Density 0.357%

    No Known Activations