© 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. 1-RES-JB
    11. 11555
    Prev
    Next
    INDEX
    Explanations

    links or references in a document

    oai_token-act-pair · gpt-3.5-turbo

    list-like structures or items presented sequentially

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utic
    -0.81
     inward
    -0.70
    orate
    -0.68
    ãĤ£
    -0.65
    20439
    -0.64
    ername
    -0.64
    ãĤ©
    -0.64
    ricular
    -0.63
     irreversible
    -0.62
    utical
    -0.61
    POSITIVE LOGITS
    ;;
    0.72
    References
    0.70
    warning
    0.68
    Synopsis
    0.66
    rawdownloadcloneembedreportprint
    0.65
     Peninsula
    0.65
    onnaissance
    0.64
    archive
    0.63
    Includes
    0.63
    cknowled
    0.63
    Activations Density 0.461%

    No Known Activations