© 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. 4-RES-JB
    11. 1868
    Prev
    Next
    INDEX
    Explanations

    occurrences of words related to practicing or training

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "practicing" and related variations

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

    No Comments

    Negative Logits
    sea
    -0.70
    by
    -0.65
    pi
    -0.64
    inki
    -0.64
    vous
    -0.63
    ¯¯¯¯
    -0.63
    quel
    -0.61
    vana
    -0.61
    izons
    -0.60
    worms
    -0.60
    POSITIVE LOGITS
     practicing
    1.00
    ctor
    0.85
     practice
    0.83
     Practice
    0.80
     pract
    0.78
    icum
    0.77
     practise
    0.76
     practiced
    0.75
     regimen
    0.75
     Practices
    0.74
    Activations Density 0.021%

    No Known Activations