© 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. 3-RES-JB
    11. 20546
    Prev
    Next
    INDEX
    Explanations

    terms related to specific individuals and organizations identified by specific acronyms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities, particularly those related to the acronym "EF."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lar
    -0.73
    flation
    -0.73
    pack
    -0.71
     Slate
    -0.67
    emon
    -0.64
     Economy
    -0.63
    )=(
    -0.62
    open
    -0.62
    DOC
    -0.62
     Osw
    -0.61
    POSITIVE LOGITS
    elaide
    0.95
    utical
    0.90
     Seym
    0.80
    ience
    0.79
    mite
    0.79
    iences
    0.78
    ederation
    0.78
    instein
    0.77
    mology
    0.75
    rees
    0.75
    Activations Density 0.031%

    No Known Activations