© 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. 9-RES-JB
    11. 3214
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to energy, power, or intensity, often with an emphasis on strength or prominence

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ene"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istani
    -0.90
    ties
    -0.88
    ernaut
    -0.78
    uitous
    -0.76
    ricane
    -0.75
    enegger
    -0.74
    lime
    -0.73
    oons
    -0.73
    icago
    -0.73
    things
    -0.73
    POSITIVE LOGITS
    uve
    1.16
    alogy
    1.08
    utics
    1.07
    agles
    1.05
     Wenger
    1.04
    volent
    1.00
    utical
    0.96
    vol
    0.88
    quin
    0.86
    vre
    0.85
    Activations Density 0.054%

    No Known Activations