© 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. 7-RES-JB
    11. 23856
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "routine."

    oai_token-act-pair · gpt-3.5-turbo

    references to routines or habitual actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    burgh
    -0.76
    iva
    -0.74
    onz
    -0.74
    owitz
    -0.73
    ippi
    -0.73
    oras
    -0.72
    arag
    -0.72
    mented
    -0.67
    essee
    -0.67
    stocks
    -0.67
    POSITIVE LOGITS
     routine
    1.11
     maintenance
    1.03
     routines
    0.96
    ized
    0.80
    outine
    0.76
     inspection
    0.76
    cy
    0.75
     tasks
    0.75
     occurrence
    0.74
    dayName
    0.74
    Activations Density 0.022%

    No Known Activations