© 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. 10405
    Prev
    Next
    INDEX
    Explanations

    terms related to physics and energy levels

    oai_token-act-pair · gpt-3.5-turbo

    references to energy in various physical contexts

    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
    ettings
    -0.82
    lihood
    -0.76
     Cause
    -0.67
     Siem
    -0.66
     Fargo
    -0.65
    gery
    -0.64
     Cla
    -0.63
    kie
    -0.63
    MSN
    -0.63
    eur
    -0.62
    POSITIVE LOGITS
     photons
    0.90
     absorption
    0.88
    llor
    0.82
     volts
    0.81
     density
    0.81
     electrons
    0.79
    inventoryQuantity
    0.79
     absorbing
    0.78
     efficient
    0.78
    frac
    0.77
    Activations Density 0.025%

    No Known Activations