© 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. 7-RES-JB
    11. 21107
    Prev
    Next
    INDEX
    Explanations

    keywords related to compilers and programming languages

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to compilers and compilation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ricular
    -0.87
    agher
    -0.87
    ometown
    -0.85
    laus
    -0.80
    nutrition
    -0.79
    oran
    -0.78
    ĸļ
    -0.77
    gren
    -0.75
    Ĥª
    -0.75
    awei
    -0.75
    POSITIVE LOGITS
     gcc
    1.00
     compiler
    0.98
     runtime
    0.95
     debug
    0.85
     GNU
    0.81
     GCC
    0.81
     Emacs
    0.80
     Runtime
    0.80
     kernels
    0.80
     error
    0.80
    Activations Density 0.077%

    No Known Activations