© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 7472
    Prev
    Next
    INDEX
    Explanations

    keywords related to electrical power and energy

    oai_token-act-pair · gpt-3.5-turbo

    references to electrical power and energy efficiency

    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
     Von
    -0.77
    ean
    -0.71
     Bei
    -0.68
    romeda
    -0.66
    ead
    -0.65
     seq
    -0.64
    roit
    -0.63
     kHz
    -0.62
     Kitt
    -0.62
     Norn
    -0.62
    POSITIVE LOGITS
    stroke
    1.09
    Reviewer
    0.94
    train
    0.93
    plant
    0.88
    boats
    0.85
    chair
    0.84
     consumption
    0.84
     outage
    0.83
    lif
    0.82
    lifting
    0.82
    Activations Density 0.026%

    No Known Activations