© 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. 3964
    Prev
    Next
    INDEX
    Explanations

    terms related to data analysis using Microsoft Excel

    oai_token-act-pair · gpt-3.5-turbo

    references to spreadsheet software and related data analysis terms

    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
    inges
    -0.86
    switch
    -0.69
    heimer
    -0.67
    §
    -0.67
     nominees
    -0.64
    lights
    -0.63
    joice
    -0.63
    req
    -0.60
    Ń
    -0.60
    eties
    -0.59
    POSITIVE LOGITS
    sheets
    1.16
     spreadsheet
    1.14
    sheet
    1.12
    ulative
    0.90
     Excel
    0.86
    arial
    0.82
    heet
    0.81
    TeX
    0.77
     sheet
    0.76
    chio
    0.75
    Activations Density 0.029%

    No Known Activations