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. 7-RES-JB
    6. 3437
    Prev
    Next
    INDEX
    Explanations

    a variety of content about different topics, including environmental issues, technology, and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    references to significant changes or challenges faced by society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scrap
    -0.73
     neighb
    -0.72
    xual
    -0.71
     grop
    -0.71
    ensical
    -0.71
     KT
    -0.69
     himself
    -0.66
     inning
    -0.65
     sculpt
    -0.65
     grips
    -0.64
    POSITIVE LOGITS
    Contents
    1.27
    Contribut
    1.23
    Overview
    1.23
    Examples
    1.22
    Spons
    1.21
    Discover
    1.20
    Supported
    1.19
    Trivia
    1.19
    Advertisements
    1.19
    References
    1.18
    Activations Density 0.428%

    No Known Activations