© 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. 10-RES-JB
    11. 20608
    Prev
    Next
    INDEX
    Explanations

    measurements related to size, thickness, or density, specifically on a scale from nanometers to microns

    oai_token-act-pair · gpt-3.5-turbo

    measurements and scientific data involving particle sizes or densities

    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
     entitlement
    -0.78
     refreshed
    -0.68
    OWS
    -0.65
     homelessness
    -0.64
    Asset
    -0.64
     bilingual
    -0.62
     benches
    -0.62
     unfinished
    -0.61
    ALTH
    -0.61
    Road
    -0.61
    POSITIVE LOGITS
     Kelvin
    1.23
     wavelength
    1.23
     trillion
    1.20
     atoms
    1.18
     nan
    1.18
    ousand
    1.15
     molecules
    1.14
     photons
    1.12
    billion
    1.11
     centimeters
    1.10
    Activations Density 0.156%

    No Known Activations