Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18297
    Prev
    Next
    INDEX
    Explanations

    keywords related to electronic circuits and circuit boards

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "circuit" in various contexts related to technology and electronics

    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
    minster
    -0.78
    ever
    -0.72
    Hispanic
    -0.68
     Ambrose
    -0.67
    oln
    -0.63
    ighter
    -0.62
     IMAGES
    -0.62
     Haku
    -0.62
     Columb
    -0.61
     Refugees
    -0.61
    POSITIVE LOGITS
     circuits
    1.11
     breaker
    1.09
     circuit
    1.05
     Circuit
    0.84
    cade
    0.84
    eering
    0.82
    dayName
    0.78
    engers
    0.76
     conduc
    0.76
     boards
    0.75
    Activations Density 0.014%

    No Known Activations