Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 13503
    Prev
    Next
    INDEX
    Explanations

    text related to software development frameworks and technologies

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and concepts related to web development frameworks and design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ylum
    -0.82
    utral
    -0.73
    cigarette
    -0.73
    gay
    -0.73
    icultural
    -0.72
    ometown
    -0.72
    liv
    -0.72
    crew
    -0.71
    incial
    -0.70
    PHOTOS
    -0.70
    POSITIVE LOGITS
     Python
    1.34
     Qt
    1.29
     Github
    1.20
     Java
    1.20
     GitHub
    1.20
     Apache
    1.19
     GHC
    1.17
     Flask
    1.17
     MySQL
    1.17
     Node
    1.16
    Activations Density 0.255%

    No Known Activations