© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 5073
    Prev
    Next
    INDEX
    Explanations

    text related to the concept of "practice."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of practice in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    worms
    -0.84
    gin
    -0.79
    yssey
    -0.78
    sea
    -0.74
    gow
    -0.70
    ï¸ı
    -0.70
    este
    -0.69
    aughter
    -0.69
    nette
    -0.67
    ilee
    -0.66
    POSITIVE LOGITS
     regimen
    0.79
     practiced
    0.74
     practice
    0.72
     practicing
    0.71
    ually
    0.70
     Practices
    0.70
     practitioner
    0.70
    FUL
    0.70
    itual
    0.69
     practices
    0.69
    Activations Density 0.052%

    No Known Activations