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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 15846
    Prev
    Next
    INDEX
    Explanations

    specific mentions of hardware components such as "Arduino" and "GPIO" pins

    oai_token-act-pair · gpt-3.5-turbo

    references to Arduino and Raspberry Pi components

    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
    phal
    -0.79
    othy
    -0.79
    lining
    -0.75
    utical
    -0.74
    othe
    -0.73
    ophysical
    -0.71
    eah
    -0.70
     plural
    -0.69
    illard
    -0.68
    utic
    -0.68
    POSITIVE LOGITS
    duino
    1.19
     Arduino
    1.08
     Leonardo
    0.99
    Pie
    0.81
    Deploy
    0.80
     hobby
    0.78
     Nano
    0.78
    Serial
    0.75
     IDE
    0.75
    eers
    0.74
    Activations Density 0.028%

    No Known Activations