© 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. 0-RES-JB
    11. 9429
    Prev
    Next
    INDEX
    Explanations

    instances of the word "regular" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "regular."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogy
    -0.75
    conom
    -0.70
    ayers
    -0.68
    hatt
    -0.68
    tek
    -0.66
     wherein
    -0.65
     Communities
    -0.64
    hunt
    -0.63
    erson
    -0.62
    ciation
    -0.61
    POSITIVE LOGITS
     regular
    3.57
    regular
    2.65
    Regular
    2.44
     Regular
    2.43
     normal
    1.76
     frequent
    1.72
     regulars
    1.72
     ordinary
    1.51
     regularly
    1.50
     periodic
    1.49
    Activations Density 0.009%

    No Known Activations