© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 18333
    Prev
    Next
    INDEX
    Explanations

    programming languages and related terms, specifically focusing on C#

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the '#' symbol, indicating references to metadata or headings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Karin
    -0.72
     Vie
    -0.70
     lev
    -0.68
     oun
    -0.68
    vation
    -0.67
     Gors
    -0.66
     deprived
    -0.64
     retired
    -0.64
     dred
    -0.63
     solitary
    -0.62
    POSITIVE LOGITS
    !/
    1.08
    define
    1.05
    wcsstore
    1.00
    @#
    0.91
    DIV
    0.88
    endif
    0.87
    HY
    0.86
    saf
    0.84
    RH
    0.83
    tm
    0.82
    Activations Density 0.009%

    No Known Activations