© 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. 4-RES-JB
    11. 17073
    Prev
    Next
    INDEX
    Explanations

    parts of code related to the C++ standard library, specifically functions and classes

    oai_token-act-pair · gpt-3.5-turbo

    references to the C++ Standard Library and related terminology

    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
    LECT
    -0.86
    meric
    -0.84
    MpServer
    -0.81
    cles
    -0.77
    stery
    -0.77
    gger
    -0.76
    stasy
    -0.75
    ramid
    -0.74
     neurot
    -0.74
    lete
    -0.72
    POSITIVE LOGITS
     Fischer
    0.72
     Budapest
    0.69
     Winged
    0.68
    insk
    0.67
     deed
    0.65
    ãĥĥãĥī
    0.64
    obyl
    0.62
     Cincinnati
    0.62
    ucky
    0.61
    andise
    0.60
    Activations Density 0.021%

    No Known Activations