© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 4524
    Prev
    Next
    INDEX
    Explanations

    references to the Arduino microcontroller and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to Arduino and related electronic components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phal
    -0.78
    ophysical
    -0.75
    othe
    -0.74
    hra
    -0.71
    ewitness
    -0.70
    utic
    -0.70
    orah
    -0.68
    othy
    -0.67
     Madden
    -0.66
    utical
    -0.66
    POSITIVE LOGITS
    duino
    1.21
     Arduino
    0.94
    Pie
    0.86
     Leonardo
    0.86
    Deploy
    0.79
     hobby
    0.74
     filament
    0.73
    eers
    0.70
    Jess
    0.70
    Fun
    0.70
    Activations Density 0.015%

    No Known Activations