© 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. 8215
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Py" followed by a single character and potentially a number, which might be related to Python programming concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to the programming language Python

    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
    agher
    -0.84
    haul
    -0.82
    Wisconsin
    -0.77
     Quinn
    -0.73
     Gallagher
    -0.72
    gerald
    -0.68
     Hernandez
    -0.68
    adata
    -0.68
    Jenn
    -0.68
     Wisconsin
    -0.67
    POSITIVE LOGITS
     Py
    3.82
     py
    3.26
    Py
    2.88
    py
    1.86
     Pyramid
    1.64
     Python
    1.61
     Pyro
    1.58
     Sph
    1.56
     pyramid
    1.54
    ython
    1.48
    Activations Density 0.030%

    No Known Activations