© 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. 13763
    Prev
    Next
    INDEX
    Explanations

    instances of the word "practicing" or words related to the act of practicing

    oai_token-act-pair · gpt-3.5-turbo

    words related to the act of practicing or rehearsing activities or skills

    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
    yssey
    -0.79
    ï¸ı
    -0.74
    by
    -0.72
    izons
    -0.71
    bang
    -0.69
    ilee
    -0.69
    ansas
    -0.68
    vana
    -0.68
    mine
    -0.67
    oho
    -0.67
    POSITIVE LOGITS
     practicing
    0.87
     regimen
    0.77
     practitioner
    0.75
     pract
    0.75
     martial
    0.74
     practice
    0.73
    icum
    0.72
     mindfulness
    0.70
     Grounds
    0.69
     sessions
    0.69
    Activations Density 0.027%

    No Known Activations