© 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 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. 0-RES-JB
    11. 12546
    Prev
    Next
    INDEX
    Explanations

    the word "cores" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to cores in computing or processing contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     piping
    -0.69
     {{
    -0.65
     jQuery
    -0.64
    imble
    -0.62
     RNC
    -0.62
     VAT
    -0.61
     Charity
    -0.61
     Patient
    -0.60
     ACL
    -0.60
     statutory
    -0.59
    POSITIVE LOGITS
     cores
    2.56
    ogical
    1.36
     Stories
    1.16
    nell
    1.15
    ogy
    1.13
     tid
    0.95
    lake
    0.93
     dens
    0.88
    LR
    0.86
     outskirts
    0.86
    Activations Density 0.033%

    No Known Activations