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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 5183
    Prev
    Next
    INDEX
    Explanations

    descriptions of properties with numerical values (e.g. measurements, quantities)

    oai_token-act-pair · gpt-3.5-turbo

    quantities and measurements related to makeup products and housing structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fears
    -0.69
     controversies
    -0.62
    nce
    -0.62
     displeasure
    -0.62
     increasingly
    -0.61
    mbudsman
    -0.61
     perceptions
    -0.61
     deadlines
    -0.60
     negativity
    -0.60
    eston
    -0.60
    POSITIVE LOGITS
     apiece
    1.73
     totaling
    1.34
     plus
    1.20
     respectively
    1.09
     crammed
    1.06
     each
    1.04
    poons
    1.04
     arranged
    1.02
     stacked
    1.00
     total
    0.98
    Activations Density 0.331%

    No Known Activations