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. 11-RES-JB
    6. 19781
    Prev
    Next
    INDEX
    Explanations

    terms related to Raspberry Pi and its accessories, including Raspberry Pi models and components such as GPIO pins and Kickstarter campaigns

    oai_token-act-pair · gpt-3.5-turbo

    references to the Raspberry Pi Zero and its features or applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illard
    -0.83
    ologne
    -0.75
     Cull
    -0.74
    Iraq
    -0.73
     attrition
    -0.72
     Louisiana
    -0.72
    lain
    -0.71
     Madden
    -0.70
     Moody
    -0.69
     ObamaCare
    -0.69
    POSITIVE LOGITS
     Raspberry
    2.03
     Arduino
    1.87
     GPIO
    1.87
    Pi
    1.80
    duino
    1.79
     Pi
    1.79
    aspberry
    1.64
     raspberry
    1.47
     IoT
    1.28
     pi
    1.27
    Activations Density 0.191%

    No Known Activations