© 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. 11-RES-JB
    11. 21968
    Prev
    Next
    INDEX
    Explanations

    phrases related to note-taking applications and productivity tools

    oai_token-act-pair · gpt-3.5-turbo

    features and capabilities of a digital note-taking application

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nat
    -0.80
    fried
    -0.78
    olph
    -0.77
    reth
    -0.74
    mask
    -0.74
     negro
    -0.74
    aterasu
    -0.73
    gypt
    -0.71
     stim
    -0.70
     tob
    -0.69
    POSITIVE LOGITS
     Dropbox
    1.93
     iCloud
    1.55
     Gmail
    1.51
     Outlook
    1.38
     Office
    1.30
     productivity
    1.27
     PowerPoint
    1.24
     spreadsheet
    1.24
     Excel
    1.22
     Documents
    1.22
    Activations Density 0.268%

    No Known Activations