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. 4-RES-JB
    6. 12685
    Prev
    Next
    INDEX
    Explanations

    various online platforms and applications such as Google Maps, Google Calendar, and Google Earth

    oai_token-act-pair · gpt-3.5-turbo

    references to Google services and applications

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

    No Comments

    Negative Logits
    ĪĴ
    -0.78
     Tale
    -0.66
    pole
    -0.66
     pipe
    -0.65
     spine
    -0.63
     knife
    -0.62
    bush
    -0.61
     saline
    -0.61
     Kits
    -0.61
    ilogy
    -0.60
    POSITIVE LOGITS
    Plex
    0.80
    vine
    0.75
    ern
    0.74
    chrome
    0.73
    enhagen
    0.73
    utters
    0.71
     Gmail
    0.71
    upload
    0.70
    maps
    0.70
    unic
    0.69
    Activations Density 0.094%

    No Known Activations