© 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. 3-RES-JB
    11. 24095
    Prev
    Next
    INDEX
    Explanations

    mentions of specific numerical values related to money or quantity

    oai_token-act-pair · gpt-3.5-turbo

    articles or determiners in the text

    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
    Edit
    -0.77
    reports
    -0.69
    Examples
    -0.65
    evidence
    -0.65
     Izan
    -0.65
    eyes
    -0.65
    End
    -0.65
    =[
    -0.63
    SOURCE
    -0.63
    Contents
    -0.62
    POSITIVE LOGITS
     lot
    1.14
     bunch
    1.09
     couple
    1.09
     handful
    1.07
    rouse
    1.06
     few
    1.02
     piece
    0.92
    ird
    0.92
    uras
    0.91
    sembly
    0.90
    Activations Density 1.003%

    No Known Activations